© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42608
    Prev
    Next
    INDEX
    Explanations

    technical terms and words related to programming and computing

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

    pro or PRO prefixes

    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
     transfieras
    -0.35
     Krakowie
    -0.35
     burbu
    -0.35
    Dimensi
    -0.35
     einzig
    -0.35
    Handlung
    -0.35
     Ausgleich
    -0.34
    ceğine
    -0.34
    限り
    -0.34
     oznac
    -0.33
    POSITIVE LOGITS
    pro
    0.59
    Pro
    0.58
    pros
    0.57
     Prop
    0.57
    opro
    0.56
    propri
    0.56
    Pru
    0.56
     pru
    0.55
     Pro
    0.54
     Pru
    0.54
    Activations Density 0.088%

    No Known Activations