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. 20-GEMMASCOPE-RES-16K
    6. 444
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness to take action or move forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating readiness or willingness to act.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    toHexString
    -0.49
     the
    -0.47
     function
    -0.36
     dipendenti
    -0.36
     Colleen
    -0.36
    moduleName
    -0.35
    nodeValue
    -0.35
     Pollack
    -0.35
    filterBy
    -0.35
    InputModule
    -0.34
    POSITIVE LOGITS
     ready
    1.50
     Ready
    1.49
    Ready
    1.41
     READY
    1.40
    ready
    1.34
    READY
    1.27
     readiness
    1.27
     Readiness
    1.14
     siap
    1.09
     prêt
    1.04
    Activations Density 0.033%

    No Known Activations