© 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. 42664
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations involving numerical values and operations

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

    volume measurements

    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
    AsUp
    -0.50
    TAWA
    -0.42
    Gemeinden
    -0.41
     mắn
    -0.40
    ArgsConstructor
    -0.38
    esModule
    -0.37
    batore
    -0.36
    ttino
    -0.36
    jspb
    -0.35
     silenzio
    -0.35
    POSITIVE LOGITS
    stylers
    0.48
    WriteAttribute
    0.48
     Bey
    0.47
     tail
    0.47
    kháu
    0.46
     Leib
    0.44
    binding
    0.43
    rest
    0.42
     bey
    0.42
    Tail
    0.41
    Activations Density 0.315%

    No Known Activations