© 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. 21760
    Prev
    Next
    INDEX
    Explanations

    text formatting or structural elements in code or documentation

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

    user prompts

    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
    tahui
    -0.40
    brough
    -0.38
    aktery
    -0.34
    AnchorTagHelper
    -0.34
    uxxxx
    -0.32
    omalainen
    -0.32
    assertThat
    -0.32
    ษัท
    -0.32
     absolutely
    -0.31
    tiert
    -0.31
    POSITIVE LOGITS
     wireType
    0.59
     يتيمه
    0.52
     &___
    0.51
     Vapor
    0.47
     termica
    0.47
    Migration
    0.46
    mtrl
    0.45
     Railways
    0.45
     rails
    0.44
    greSQL
    0.44
    Activations Density 0.000%

    No Known Activations