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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6529
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical notation or discussion related to statistical or probabilistic models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewInit
    -0.98
    MigrationBuilder
    -0.94
    parsedMessage
    -0.84
     estekak
    -0.83
    OGND
    -0.77
     FetchType
    -0.75
    GEBURTS
    -0.75
    ########.
    -0.74
    WebVitals
    -0.74
    twimg
    -0.74
    POSITIVE LOGITS
     kokona
    0.43
     computadoras
    0.42
     puntas
    0.41
     orejas
    0.40
     península
    0.40
     preguntó
    0.40
     perlas
    0.40
     macetas
    0.40
     Socialista
    0.39
     Mannschaft
    0.39
    Activations Density 0.228%

    No Known Activations