© 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. 12419
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to partitions and tableaux

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

    obtained or formed

    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
     propOrder
    -0.54
    principalColumn
    -0.48
    MigrationBuilder
    -0.47
    setContentView
    -0.45
     Scalars
    -0.45
    帖最后由
    -0.41
    printStats
    -0.40
    layoutControl
    -0.40
    AsStream
    -0.38
     yaiba
    -0.38
    POSITIVE LOGITS
     obtained
    1.84
    obtained
    1.66
     Obtained
    1.52
     derived
    1.41
     achieved
    1.37
     formed
    1.30
     ottenuto
    1.27
     generated
    1.24
     created
    1.24
     obtenu
    1.22
    Activations Density 0.450%

    No Known Activations