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. 15782
    Prev
    Next
    INDEX
    Explanations

    references to social justice and representation issues

    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
    BeginInit
    -0.68
    rxjs
    -0.57
     kesi
    -0.51
     dipende
    -0.50
     consolid
    -0.50
     improvis
    -0.48
     intress
    -0.48
     interdependence
    -0.47
     ſhe
    -0.47
     temporales
    -0.47
    POSITIVE LOGITS
    mybatisplus
    0.71
     moral
    0.69
     pinulongan
    0.69
     offensive
    0.68
     censor
    0.66
     sexual
    0.65
     Moral
    0.65
     objectionable
    0.63
    ⓧ
    0.61
    Contro
    0.60
    Activations Density 0.669%

    No Known Activations