Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7735
    Prev
    Next
    INDEX
    Explanations

    elements related to form interactions and user inputs in web interfaces

    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
     intptr
    -0.53
    UnusedPrivate
    -0.51
    RTEX
    -0.49
     contextLoads
    -0.48
     يتيمه
    -0.48
     الرياضيه
    -0.48
     ModelExpression
    -0.47
    léans
    -0.47
    featureID
    -0.46
    <0xF2>
    -0.45
    POSITIVE LOGITS
     submit
    1.60
    submit
    1.48
     Submit
    1.47
    Submit
    1.45
     SUBMIT
    1.34
    SUBMIT
    1.27
     submitting
    1.25
     submits
    1.23
    提交
    1.17
     submitted
    1.13
    Activations Density 0.295%

    No Known Activations