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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11857
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and symbols related to algebraic structures

    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
    ViewImports
    -0.72
     مرئيه
    -0.62
    OGND
    -0.59
     ब्रेकडाउन
    -0.54
     disambiguazione
    -0.52
    BufferException
    -0.49
    StoryboardSegue
    -0.49
    ]")]
    -0.49
    rungsseite
    -0.48
     فريبيس
    -0.47
    POSITIVE LOGITS
    ㄨ
    0.38
    idhi
    0.37
    MigrationBuilder
    0.36
    izoen
    0.36
    saraba
    0.35
     &___
    0.35
     rep
    0.34
    idas
    0.33
    ectoria
    0.33
    insics
    0.33
    Activations Density 1.216%

    No Known Activations