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. 97580
    Prev
    Next
    INDEX
    Explanations

    references to investigations and their outcomes

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

    investigation into results

    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
    ंदीखरीदारी
    -0.82
     useAppContext
    -0.65
    bootstrapcdn
    -0.60
    ⟬
    -0.56
     indígen
    -0.56
    AnimationsModule
    -0.56
    BibitemShut
    -0.55
     Geſch
    -0.55
     princí
    -0.55
    ſſung
    -0.54
    POSITIVE LOGITS
     investigation
    1.20
     investigations
    1.10
     Investigation
    1.09
    investigation
    1.08
     Investigations
    1.05
    Investigation
    0.98
     INVESTIGATION
    0.98
     INVESTIG
    0.96
     investig
    0.94
     investigate
    0.94
    Activations Density 0.050%

    No Known Activations