© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9468
    Prev
    Next
    INDEX
    Explanations

    information related to function signatures and type definitions in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    layoutParams
    -0.53
    </h2>
    -0.49
     hell
    -0.48
     đại
    -0.48
    vane
    -0.47
    Aiheesta
    -0.47
     (
    -0.46
    mehl
    -0.46
     Gra
    -0.45
     of
    -0.45
    POSITIVE LOGITS
    >)
    2.26
    >;
    2.20
    >,
    2.15
    >.
    2.00
    >"
    1.78
    >:
    1.75
    >\
    1.72
    >'
    1.64
    >}
    1.60
    >]
    1.57
    Activations Density 0.062%

    No Known Activations