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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 11351
    Prev
    Next
    INDEX
    Explanations

    sentences that convey criticism or condemnation of certain behaviors or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.96
     Houſe
    -0.90
     itſelf
    -0.89
     ſche
    -0.88
     Reſ
    -0.87
     Efq
    -0.86
     Majefty
    -0.85
     iſt
    -0.85
     myſelf
    -0.84
    amaño
    -0.84
    POSITIVE LOGITS
     [
    0.66
    AndEndTag
    0.58
    [
    0.54
    yyj
    0.50
    -[
    0.48
     $[
    0.44
    +[
    0.44
     ${
    0.43
    ,[
    0.42
     Brandt
    0.42
    Activations Density 0.130%

    No Known Activations