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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 124479
    Prev
    Next
    INDEX
    Explanations

    measurements and competition formats in sports

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

    sports events with distances

    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
    expandindo
    -0.60
     OMITBAD
    -0.52
     Inscrivez
    -0.50
    verwijspagina
    -0.48
     inférieure
    -0.47
     enfans
    -0.46
     normaux
    -0.46
     Púb
    -0.45
     Etats
    -0.45
     Herramientas
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.59
    complexContent
    0.57
    MigrationBuilder
    0.55
     mile
    0.52
     McE
    0.51
    athlon
    0.50
     waivers
    0.49
     sprints
    0.47
     graded
    0.46
     Mile
    0.45
    Activations Density 0.007%

    No Known Activations