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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 76968
    Prev
    Next
    INDEX
    Explanations

    phrases related to the finalization and approval of documents or manuscripts

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

    final approval or version

    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
    NUMX
    -0.57
    WritableDatabase
    -0.56
     RTE
    -0.55
     autorytatywna
    -0.54
     MEC
    -0.52
    batore
    -0.52
    Gruss
    -0.51
    ComponentScan
    -0.51
    hops
    -0.50
     moschino
    -0.50
    POSITIVE LOGITS
     final
    1.26
    final
    1.05
    Final
    0.95
     Final
    0.92
    FINAL
    0.91
     FINAL
    0.90
     endgül
    0.73
     finalized
    0.70
     оконча
    0.69
     finalize
    0.69
    Activations Density 0.012%

    No Known Activations