© 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. 2-GEMMASCOPE-RES-16K
    11. 4027
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed identifiers and occurrences of varying levels of nested structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assignee
    -0.85
    neſs
    -0.84
    )");
    -0.83
     faſt
    -0.78
    )";
    -0.75
     μή
    -0.74
    %");
    -0.73
    GHIJKLM
    -0.73
     Houſe
    -0.72
     pleaſure
    -0.71
    POSITIVE LOGITS
     _
    1.68
    ._
    1.55
    (_
    1.32
     (_
    1.18
    [_
    1.14
    ,_
    1.12
    =_
    1.11
    :_
    1.07
    ::_
    1.05
    ?_
    1.04
    Activations Density 0.401%

    No Known Activations