© 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. 14718
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and identifiers, particularly in programming languages

    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
     queſta
    -0.86
    MessageTagHelper
    -0.81
    bootstrapcdn
    -0.81
     Houſe
    -0.80
    tagHelperRunner
    -0.79
     kasarigan
    -0.78
     ſei
    -0.78
    ſelves
    -0.77
     CreateTagHelper
    -0.76
     GenerationType
    -0.73
    POSITIVE LOGITS
     *
    1.05
    *
    1.03
    /
    0.41
    -
    0.40
    //
    0.40
    </i>
    0.39
    </em>
    0.39
    »
    0.35
    ?
    0.34
    ...
    0.34
    Activations Density 1.360%

    No Known Activations