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. 7813
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to firearms and shooting

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

    shooting and firing

    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
    transQ
    -0.44
    verwijspagina
    -0.37
    setTransform
    -0.35
     indisponible
    -0.34
    WriteAttribute
    -0.34
     Bewußt
    -0.31
     ministro
    -0.31
    ListItemIcon
    -0.31
     poveznice
    -0.31
     kada
    -0.30
    POSITIVE LOGITS
     surla
    0.57
     pageContext
    0.51
     ferroviaire
    0.50
    出版年
    0.49
    PyExc
    0.48
    탤
    0.47
    tangentMode
    0.46
    ➯
    0.45
    acus
    0.44
    ">—
    0.44
    Activations Density 0.011%

    No Known Activations