© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 76465
    Prev
    Next
    INDEX
    Explanations

    references to game mechanics or terminology related to a specific gaming context

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

    KOF or drug treatment

    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
    存于互联网档案馆
    -0.68
     []:
    -0.40
    esco
    -0.32
    ecera
    -0.32
    ir
    -0.31
    ervlak
    -0.31
    load
    -0.31
    interopRequire
    -0.31
     cherchés
    -0.30
    شفى
    -0.30
    POSITIVE LOGITS
     Kombat
    0.62
    twimg
    0.56
     चीज़ों
    0.53
    AddTagHelper
    0.50
    richTextPanel
    0.48
    DebuggerStep
    0.47
    majánló
    0.47
     Capcom
    0.46
    клопе
    0.46
    UnusedPrivate
    0.46
    Activations Density 0.173%

    No Known Activations