© 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. 38-GEMMASCOPE-RES-16K
    6. 14590
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rujuakan
    -0.59
    reportWebVitals
    -0.49
    blest
    -0.49
    ьаж
    -0.47
    "]="
    -0.47
    RegressionTest
    -0.46
    gent
    -0.46
    MessageTagHelper
    -0.46
    etc
    -0.45
    GTC
    -0.44
    POSITIVE LOGITS
     >=
    0.50
    󠁿
    0.43
     +=
    0.43
     precisione
    0.43
     elettrico
    0.43
     pulito
    0.41
     ==
    0.41
     mesmos
    0.38
     digitais
    0.38
    tagHelperRunner
    0.38
    Activations Density 0.243%

    No Known Activations