© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5948
    Prev
    Next
    INDEX
    Explanations

    references to service or package offerings in a business context

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

    Deals, packages, or offers

    np_acts-logits-general · gemini-2.0-flash

    options, packages, and deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.47
     onderwerp
    -0.38
    enfance
    -0.38
     yumu
    -0.37
    nextDouble
    -0.37
     récentes
    -0.36
    pendenti
    -0.36
    Ecotoxicity
    -0.36
     traductions
    -0.35
    orcid
    -0.35
    POSITIVE LOGITS
     option
    0.93
     options
    0.88
     Option
    0.81
     packages
    0.79
    Option
    0.78
     package
    0.75
    options
    0.75
    option
    0.73
     Options
    0.72
     priced
    0.71
    Activations Density 0.232%

    No Known Activations