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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8080
    Prev
    Next
    INDEX
    Explanations

    technical terms related to commands and command-line interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rotum
    -0.42
     Vereinigte
    -0.40
    <bos>
    -0.40
    issau
    -0.39
    ̍
    -0.38
     Hälfte
    -0.38
    s
    -0.38
     Relaciones
    -0.37
    Bissau
    -0.36
    Aug
    -0.35
    POSITIVE LOGITS
     Command
    1.27
     command
    1.19
     ICommand
    1.16
     SqlCommand
    1.14
     Commands
    1.13
    Command
    1.09
     COMMAND
    1.05
     commands
    1.05
    command
    1.03
     Commando
    1.01
    Activations Density 0.025%

    No Known Activations