© 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. 1-GEMMASCOPE-RES-16K
    6. 8112
    Prev
    Next
    INDEX
    Explanations

    terms related to "fine" particles and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    criminator
    -0.42
     bocca
    -0.42
     '{@
    -0.39
     vlá
    -0.38
    writeField
    -0.38
     createdBy
    -0.37
    entityManager
    -0.37
     edelstahl
    -0.36
    yyb
    -0.35
     circonst
    -0.35
    POSITIVE LOGITS
     confined
    0.92
     fine
    0.82
     restricted
    0.79
    fine
    0.76
     finite
    0.73
    Fine
    0.70
     Fine
    0.69
     Finite
    0.69
     transitioning
    0.69
    transition
    0.68
    Activations Density 0.346%

    No Known Activations