© 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. 28-GEMMASCOPE-RES-16K
    11. 8231
    Prev
    Next
    INDEX
    Explanations

    phrases related to powerful abilities or attacks

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

    Comes before "a," "the," or "Meteor"

    np_acts-logits-general · gemini-2.0-flash

    action attack finishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ér
    -0.27
     visibly
    -0.26
     closet
    -0.25
     popol
    -0.25
    garek
    -0.25
     évaluations
    -0.25
    关注
    -0.25
     råd
    -0.25
     evidentiary
    -0.25
     general
    -0.25
    POSITIVE LOGITS
    principalColumn
    0.74
    ViewImports
    0.69
    MessageOf
    0.68
     attack
    0.66
     Roskov
    0.66
     attaque
    0.65
     مشين
    0.65
    ɵɵ
    0.64
    attacks
    0.63
    :✨
    0.62
    Activations Density 0.426%

    No Known Activations