© 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. 9667
    Prev
    Next
    INDEX
    Explanations

    terms related to social obligation, choice, and medical conditions

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

    active verbal phrases expressing enthusiasm or persuasion.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    modal verbs and auxiliary constructions expressing obligation, necessity, or strong recommendation.

    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
    localctx
    -0.63
     EconPapers
    -0.61
    expandindo
    -0.58
     '\\;'
    -0.56
     nahilalakip
    -0.52
     للمعارف
    -0.51
    ConverterFactory
    -0.49
    PerformLayout
    -0.47
    hyrchwyd
    -0.47
     مرئيه
    -0.47
    POSITIVE LOGITS
     consuming
    1.06
     consumption
    1.06
     consume
    1.02
     eating
    0.88
     viewing
    0.87
     drinking
    0.86
     eat
    0.85
     consumir
    0.84
     consumo
    0.84
     watching
    0.83
    Activations Density 0.797%

    No Known Activations