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. 11774
    Prev
    Next
    INDEX
    Explanations

    code elements related to database query construction and manipulation

    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
     kasarigan
    -0.67
    出版年
    -0.52
    thâu
    -0.50
     MainAxisSize
    -0.49
     CURIAM
    -0.48
    wantErr
    -0.48
    RTSC
    -0.48
    SOUNDBITE
    -0.47
     صوتيه
    -0.47
     censiti
    -0.47
    POSITIVE LOGITS
     utafitiHapana
    0.48
    handeling
    0.41
    八
    0.41
     quita
    0.40
    Читати
    0.40
     vôtre
    0.38
     répé
    0.38
    int
    0.38
     présente
    0.38
    ServiceProvider
    0.38
    Activations Density 0.424%

    No Known Activations