© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11374
    Prev
    Next
    INDEX
    Explanations

    terms associated with heavy machinery or construction-related topics.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms related to heavy machinery and construction projects.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to "heavy" or "heavyweight", particularly in contexts describing physical objects, equipment, materials, or metaphorical uses of "heavy" to indicate importance or significance.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "heavy" and related items

    np_acts-logits-general · gemini-2.0-flash

    heavy + noun combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.84
    PreferredItem
    -0.70
     виправивши
    -0.69
    parsedMessage
    -0.68
    XmlAccessorType
    -0.63
    Hochspringen
    -0.62
    хьтан
    -0.59
    __*/
    -0.57
    :✨
    -0.56
     ویکی‌پدی
    -0.56
    POSITIVE LOGITS
     Heavy
    1.26
    Heavy
    1.25
    weights
    1.24
     heavy
    1.23
     HEAVY
    1.20
    heavy
    1.20
     duty
    1.15
     heaviest
    1.10
    duty
    1.08
     Duty
    1.05
    Activations Density 0.042%

    No Known Activations