© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16145
    Prev
    Next
    INDEX
    Explanations

    elements of uncertainty or precarious situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    personal pronouns referring to people facing difficult circumstances or negative consequences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calma
    -0.45
     ویکی‌پدی
    -0.40
     poros
    -0.38
    sizeof
    -0.38
     kasarigan
    -0.36
    renderItem
    -0.32
    PARATUS
    -0.32
    owicz
    -0.31
    不愧
    -0.31
    errHandler
    -0.31
    POSITIVE LOGITS
     terpaksa
    1.01
     forced
    0.98
     losing
    0.93
     выну
    0.91
     loses
    0.89
     gezwungen
    0.88
     unable
    0.85
     helplessly
    0.84
     Forced
    0.84
     lost
    0.82
    Activations Density 0.718%

    No Known Activations