© 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. 12-GEMMASCOPE-RES-16K
    11. 5653
    Prev
    Next
    INDEX
    Explanations

    elements related to appreciation or enthusiasm for design, food, and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.37
     continúas
    -0.37
    RectangleBorder
    -0.33
    arrings
    -0.33
    теристики
    -0.33
    etcode
    -0.32
    WriteBarrier
    -0.32
    ulemon
    -0.32
     Ness
    -0.32
    writeField
    -0.32
    POSITIVE LOGITS
    Kjelder
    0.59
    ThroughAttribute
    0.52
    Viited
    0.52
    launched
    0.48
    tagHelperRunner
    0.47
    Programme
    0.47
    CppMethod
    0.46
    Šalt
    0.46
    programme
    0.46
    ="@+
    0.46
    Activations Density 1.257%

    No Known Activations