© 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. 3-GEMMASCOPE-RES-16K
    11. 2048
    Prev
    Next
    INDEX
    Explanations

    ellipses or truncations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glyphicon
    -0.62
     sub
    -0.60
     un
    -0.60
    nant
    -0.59
     in
    -0.59
     the
    -0.57
     flag
    -0.57
     id
    -0.55
     or
    -0.55
    fang
    -0.54
    POSITIVE LOGITS
    ...
    2.45
    ,...
    2.27
    !...
    2.26
    ?...
    2.16
    ....
    2.14
     ...
    2.13
    '...
    2.12
    )...
    2.11
    ..."
    2.08
    ...,
    2.07
    Activations Density 0.129%

    No Known Activations