© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10765
    Prev
    Next
    INDEX
    Explanations

    conditional statements or scenarios involving "if" and "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "if", "when", or "where"

    np_acts-logits-general · gemini-2.0-flash

    if followed by noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EFIAPI
    -0.45
     act
    -0.37
    act
    -0.34
     takeaway
    -0.33
     acto
    -0.33
     puis
    -0.33
    @@
    -0.33
     جل
    -0.33
     fin
    -0.32
     word
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.75
    IVEREF
    0.69
    UnusedPrivate
    0.67
    jména
    0.67
     jeżeli
    0.64
     Meksiku
    0.63
     когато
    0.62
     dacă
    0.62
     wanneer
    0.61
     eğer
    0.60
    Activations Density 0.815%

    No Known Activations