© 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. 41-GEMMASCOPE-RES-16K
    11. 7032
    Prev
    Next
    INDEX
    Explanations

    concepts related to media agreements and collaborations in news broadcasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.52
    __":
    -0.47
     JpaRepository
    -0.46
    AndroidJUnit
    -0.45
    ngrx
    -0.45
    このまま
    -0.44
    RectangleBorder
    -0.44
     ExecuteAsync
    -0.43
    providedIn
    -0.42
    췄
    -0.42
    POSITIVE LOGITS
     usually
    3.23
     often
    2.77
    usually
    2.72
     typically
    2.64
     Usually
    2.61
    Usually
    2.61
     обычно
    2.50
     biasanya
    2.34
     geralmente
    2.33
     generally
    2.31
    Activations Density 2.428%

    No Known Activations