© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11067
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions of doubt

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

    Contractions with "t" as the activating token

    np_acts-logits-general · gemini-2.0-flash

    i dont

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.69
    be
    -0.55
    Swift
    -0.54
     soient
    -0.53
    Be
    -0.50
     détaillé
    -0.49
     seront
    -0.47
     Be
    -0.47
     sebelumnya
    -0.47
    hå
    -0.45
    POSITIVE LOGITS
    LookAnd
    1.24
     need
    0.96
     ModelExpression
    0.92
    ⓧ
    0.90
    ########.
    0.88
     belong
    0.88
    #+#
    0.87
     know
    0.87
     deserve
    0.85
     Réponses
    0.85
    Activations Density 0.169%

    No Known Activations