Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 92173
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to auditing and regulatory issues

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

    publicly listed companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.54
     للاسماء
    -0.48
    writeFieldEnd
    -0.47
    LayoutConstraint
    -0.46
    MigrationBuilder
    -0.45
    WriteTagHelper
    -0.45
     дописавши
    -0.44
    migrationBuilder
    -0.42
     createSlice
    -0.42
    WillAppear
    -0.42
    POSITIVE LOGITS
     publicly
    0.42
    Geografía
    0.41
     onResponse
    0.41
    INUM
    0.39
    ensee
    0.38
     Listed
    0.38
    ceng
    0.38
     Roskov
    0.37
     listed
    0.37
     pubb
    0.37
    Activations Density 0.061%

    No Known Activations