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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11649
    Prev
    Next
    INDEX
    Explanations

    words related to social or cultural issues combined with phrases indicating negative implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zijne
    -0.49
     conformidad
    -0.44
     gebouw
    -0.44
     lunghezza
    -0.42
     suaminya
    -0.42
     acompañada
    -0.42
    extrême
    -0.42
     corações
    -0.42
     resolução
    -0.41
     llorando
    -0.41
    POSITIVE LOGITS
     batt
    0.54
    PerformLayout
    0.53
     frie
    0.51
    الحياه
    0.47
     slag
    0.47
     remedial
    0.47
    WriteLiteral
    0.47
    sendRedirect
    0.46
     sena
    0.45
     bati
    0.45
    Activations Density 1.243%

    No Known Activations