© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 12161
    Prev
    Next
    INDEX
    Explanations

    descriptive language relating to sensory experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uncher
    -0.64
     Always
    -0.58
    <bos>
    -0.54
    Always
    -0.52
     monthly
    -0.51
    天天
    -0.50
    bal
    -0.49
     weekly
    -0.48
    SizeMode
    -0.48
    每次
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.77
    dafx
    0.75
     AssemblyCulture
    0.73
    Переваги
    0.67
     feeling
    0.66
     thoughts
    0.64
    esterday
    0.62
     soudain
    0.61
     JpaRepository
    0.61
    tagHelperRunner
    0.60
    Activations Density 0.229%

    No Known Activations