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. 124755
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing and integrity verification

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

    license identifiers and integrity checks

    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
     fotográfico
    -0.43
     Fotografía
    -0.40
     manifestación
    -0.40
     wiedzy
    -0.38
     informacija
    -0.36
     výstav
    -0.35
     contemporáneo
    -0.35
     svět
    -0.34
     pungkasnya
    -0.34
     manifestaciones
    -0.33
    POSITIVE LOGITS
    TabIndex
    1.05
    CreateModel
    0.82
     istore
    0.70
    offsetof
    0.67
    AnchorStyles
    0.66
    ########.
    0.66
    !*\
    0.61
    migrationBuilder
    0.59
     cinder
    0.58
    ScopeManager
    0.58
    Activations Density 0.001%

    No Known Activations