© 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. 24-GEMMASCOPE-RES-16K
    11. 5726
    Prev
    Next
    INDEX
    Explanations

    assertive statements related to critiques or evaluations

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

    Preceding "many" or sentence interjections

    np_acts-logits-general · gemini-2.0-flash

    though many strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deliberate
    -0.32
     unterschiedlich
    -0.32
     רבה
    -0.31
     بیشتری
    -0.31
     nghiên
    -0.30
    öhne
    -0.30
     Deliber
    -0.30
     combinação
    -0.30
    aturing
    -0.30
     prototype
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    exitRule
    0.68
     exceptions
    0.60
    لينكات
    0.60
    hyrchwyd
    0.59
     GenerationType
    0.58
    だけは
    0.57
    Diweddarwch
    0.57
     noDo
    0.56
    唯有
    0.55
    Activations Density 0.300%

    No Known Activations