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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9111
    Prev
    Next
    INDEX
    Explanations

    highly specific names or technical terms related to specialized fields.

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

    scientific terminology related to chemistry and materials science, with a focus on specific substances and technical details.

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

    names starting with "Hal", particularly proper nouns like names or company names.

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

    following "Hal" or "Hall"

    np_acts-logits-general · gemini-2.0-flash

    Hal and variations

    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
     resourceCulture
    -0.93
    principalTable
    -0.90
     <=",
    -0.80
    AndEndTag
    -0.76
     continúas
    -0.75
    elemField
    -0.74
    ftagPool
    -0.73
    setVerticalGroup
    -0.72
     виправивши
    -0.71
    yntaxException
    -0.71
    POSITIVE LOGITS
     Hal
    0.74
     hal
    0.67
    Hal
    0.64
     HAL
    0.61
    hal
    0.59
    HAL
    0.51
     HALL
    0.46
    Referensi
    0.44
    堂
    0.43
     halls
    0.43
    Activations Density 0.072%

    No Known Activations