© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7490
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    úgó
    -0.41
    äjä
    -0.35
     Wicidata
    -0.33
    culada
    -0.32
    vább
    -0.32
     sobran
    -0.32
     BrowserRouter
    -0.31
    rid
    -0.31
     "}";
    -0.31
    MigrationBuilder
    -0.30
    POSITIVE LOGITS
     require
    3.13
     requires
    3.11
     requiring
    2.92
     Requires
    2.88
     Require
    2.75
    require
    2.67
    requires
    2.67
    Requires
    2.64
    Require
    2.47
     wymaga
    2.45
    Activations Density 1.651%

    No Known Activations