© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 52
    Prev
    Next
    INDEX
    Explanations

    words related to utility and helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.67
    oneofs
    -0.61
    CommandText
    -0.57
    sizeCache
    -0.57
     increí
    -0.57
    ſelf
    -0.56
     queſta
    -0.56
     ſind
    -0.55
    rungsseite
    -0.55
     سكانية
    -0.55
    POSITIVE LOGITS
    y
    0.41
    s
    0.35
    ness
    0.33
     hints
    0.32
     intptr
    0.31
    ../
    0.30
     Helpful
    0.29
     hint
    0.29
    Vos
    0.29
    ','',
    0.29
    Activations Density 0.192%

    No Known Activations