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. 6946
    Prev
    Next
    INDEX
    Explanations

    references to antibiotics and their chemical 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
    通
    -0.43
    ionized
    -0.40
     لح
    -0.40
    getCmp
    -0.39
     公
    -0.38
     setup
    -0.38
     verg
    -0.36
     walk
    -0.36
     Leven
    -0.35
     manager
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.73
     såsom
    0.64
    enderror
    0.63
     propOrder
    0.60
    parsedMessage
    0.59
    rungsseite
    0.59
     kaarangay
    0.59
    MigrationBuilder
    0.58
    Datuak
    0.57
    principalColumn
    0.57
    Activations Density 1.319%

    No Known Activations