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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8148
    Prev
    Next
    INDEX
    Explanations

    HTML block elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.99
     (
    -0.82
    ?
    -0.80
     .
    -0.80
    \
    -0.79
     B
    -0.76
    ;
    -0.76
    1
    -0.75
     \
    -0.74
     U
    -0.74
    POSITIVE LOGITS
     itſelf
    1.63
     Efq
    1.51
     myſelf
    1.50
    ſelves
    1.34
     ſeveral
    1.34
     faſt
    1.31
     themſelves
    1.25
     pleaſure
    1.22
     purpoſe
    1.22
     doubtnut
    1.20
    Activations Density 0.066%

    No Known Activations