© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 37905
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to contracts and entitlements

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

    promissory notes and travelers checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RefNanny
    -0.45
     jadx
    -0.44
    cinct
    -0.43
    liceerd
    -0.42
    AndEndTag
    -0.41
     neighbors
    -0.40
     virgen
    -0.40
    AddTagHelper
    -0.40
     спу
    -0.39
    ɵɵ
    -0.39
    POSITIVE LOGITS
     promissory
    0.86
     notes
    0.68
     Notes
    0.64
    issory
    0.64
     negotiable
    0.62
     Negotiable
    0.61
     promesse
    0.60
    notes
    0.59
     promise
    0.56
     note
    0.56
    Activations Density 0.051%

    No Known Activations