© 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. 69348
    Prev
    Next
    INDEX
    Explanations

    references to serialized data and its related properties

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

    Java JSON serialization with @SerializedName

    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
     kasarigan
    -0.68
    bootstrapcdn
    -0.52
    ChildScrollView
    -0.52
     initComponents
    -0.51
     AssemblyTitle
    -0.50
    TestingModule
    -0.50
     kaynağından
    -0.48
     ContentValues
    -0.48
    gameserver
    -0.47
    忑
    -0.46
    POSITIVE LOGITS
     Jackson
    0.56
    Jackson
    0.50
    jackson
    0.50
     Json
    0.49
     JSON
    0.48
    fasterxml
    0.48
    json
    0.47
    httphttps
    0.46
     json
    0.45
    JSON
    0.45
    Activations Density 0.003%

    No Known Activations