© 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. 38-GEMMASCOPE-RES-16K
    11. 7292
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in code blocks

    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
    ,
    -0.38
     uses
    -0.37
    さて
    -0.34
     primarily
    -0.33
     utilisons
    -0.33
    -
    -0.32
     looks
    -0.31
    .
    -0.31
     depends
    -0.31
    ↵↵↵
    -0.31
    POSITIVE LOGITS
    featureID
    0.85
    #+#
    0.84
     StringTokenizer
    0.83
    NameInMap
    0.79
    principalColumn
    0.77
    aimeJ
    0.76
     queſta
    0.75
     tartalomajánló
    0.75
    webElementGuid
    0.74
     HttpNotFound
    0.74
    Activations Density 0.087%

    No Known Activations