Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5988
    Prev
    Next
    INDEX
    Explanations

    instances of reliance or dependence on external factors or systems

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

    "rely" or "relying" followed by "on"

    np_acts-logits-general · gemini-2.0-flash

    rely heavily on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.91
     transfieras
    -0.85
    ///</
    -0.80
    StructEnd
    -0.76
    withIdentifier
    -0.75
    OrNil
    -0.70
    XmlAccessorType
    -0.70
     ویکی‌پدی
    -0.66
     HasFactory
    -0.66
    bootstrapcdn
    -0.65
    POSITIVE LOGITS
     heavily
    0.79
     positively
    0.68
     strongly
    0.66
     extensively
    0.66
     greatly
    0.65
     inwardly
    0.64
     favorably
    0.63
     migh
    0.62
     intensely
    0.62
     externally
    0.62
    Activations Density 0.305%

    No Known Activations