© 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. 3-GEMMASCOPE-RES-16K
    6. 8018
    Prev
    Next
    INDEX
    Explanations

    terms related to utility or usefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.50
     vlož
    -0.45
     fotográfico
    -0.45
    ConstraintMaker
    -0.45
    DataSnapshot
    -0.44
    ServletConfig
    -0.44
     kysy
    -0.42
     clínico
    -0.41
     Eindruck
    -0.41
     skolen
    -0.40
    POSITIVE LOGITS
     utility
    2.16
    Util
    2.13
     Util
    2.09
     util
    2.06
     Utility
    1.95
     utilities
    1.90
     Utilities
    1.80
    util
    1.79
    Utility
    1.75
    utility
    1.71
    Activations Density 0.084%

    No Known Activations