© 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. 8813
    Prev
    Next
    INDEX
    Explanations

    linguistic components and structure within written 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
    時的
    -0.36
    ๆ
    -0.34
     Gunter
    -0.34
    orki
    -0.34
    temi
    -0.33
    Друзья
    -0.33
    度は
    -0.33
    之一
    -0.33
    Regards
    -0.32
     alike
    -0.32
    POSITIVE LOGITS
     JpaRepository
    0.64
     propOrder
    0.62
    enterOuterAlt
    0.60
    Personensuche
    0.59
     kasarigan
    0.57
     nakalista
    0.57
    MessageOf
    0.54
    gdala
    0.53
    دانشنامهٔ
    0.52
    utives
    0.52
    Activations Density 0.151%

    No Known Activations