© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the name "Har"

    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
    Népesség
    -0.41
     Sandi
    -0.40
     Luci
    -0.33
    què
    -0.33
    ameran
    -0.33
    NullCheck
    -0.32
    Kevin
    -0.32
    volve
    -0.32
    endregion
    -0.32
    Fp
    -0.32
    POSITIVE LOGITS
     Har
    0.79
    Har
    0.72
     har
    0.72
     HAR
    0.68
     utafitiHapana
    0.59
    HAR
    0.58
    devamını
    0.54
    帖最后由
    0.54
    Gambas
    0.54
     Chwiliwch
    0.54
    Activations Density 0.211%

    No Known Activations