© 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. 37-GEMMASCOPE-RES-16K
    11. 4026
    Prev
    Next
    INDEX
    Explanations

    terms related to positive and negative results or values in a diagnostic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.56
    chom
    -0.43
    riever
    -0.39
    izieren
    -0.39
    Pozri
    -0.39
    期刊论文
    -0.38
     useParams
    -0.37
    rus
    -0.37
    зре
    -0.37
     méd
    -0.36
    POSITIVE LOGITS
     feedback
    0.70
     reinforcement
    0.69
     feedbacks
    0.63
     vibes
    0.62
     connotation
    0.59
     connotations
    0.57
     Reinforcement
    0.56
     sentiment
    0.56
     impact
    0.55
    feedback
    0.55
    Activations Density 0.381%

    No Known Activations