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. 15384
    Prev
    Next
    INDEX
    Explanations

    references to development and production processes

    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
     يتيمه
    -0.64
     betweenstory
    -0.61
     ब्रेकडाउन
    -0.59
     noDo
    -0.58
    transQ
    -0.52
    Derp
    -0.49
    principalTable
    -0.49
    principalColumn
    -0.48
    uestamente
    -0.47
     فريبيس
    -0.47
    POSITIVE LOGITS
     similarly
    0.83
     likewise
    0.81
     also
    0.79
     ebenfalls
    0.78
     similar
    0.71
     też
    0.67
     тоже
    0.66
    も同じ
    0.62
    ditto
    0.60
     ähnliche
    0.59
    Activations Density 0.829%

    No Known Activations