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. 11-GEMMASCOPE-RES-16K
    6. 8478
    Prev
    Next
    INDEX
    Explanations

    references to changes in intensity or frequency in a conversation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itsubishi
    -0.56
     manganese
    -0.55
    Personensuche
    -0.52
     Manganese
    -0.50
    arangay
    -0.50
    harm
    -0.48
     titanium
    -0.48
    meaning
    -0.48
     الحره
    -0.47
    forever
    -0.47
    POSITIVE LOGITS
    msubsup
    0.39
    所
    0.37
    routeProvider
    0.36
     WebDriverWait
    0.36
     wireType
    0.33
    XmlAccessType
    0.33
    XmlAccessorType
    0.31
    ImageField
    0.31
    migrationBuilder
    0.30
    setOnItem
    0.30
    Activations Density 0.372%

    No Known Activations