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. 113699
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to algorithms and computational methods

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

    process or method description

    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
    ]--;
    -0.54
    RegressionTest
    -0.51
    Demografía
    -0.46
    GEBURTS
    -0.46
     دیکھیے
    -0.45
    __*/
    -0.44
    ⋙
    -0.44
     profiler
    -0.43
     Biv
    -0.42
    PathVariable
    -0.41
    POSITIVE LOGITS
     ligiloj
    0.46
     détermination
    0.46
     puentes
    0.45
     sagesse
    0.45
     estí
    0.44
     management
    0.44
     řízení
    0.43
     cuidadosamente
    0.43
    Gön
    0.42
     sabores
    0.41
    Activations Density 0.764%

    No Known Activations