© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4617
    Prev
    Next
    INDEX
    Explanations

    references to personal and collective experiences and relationships

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

    Prepositions like "on behalf", "on the same"

    np_acts-logits-general · gemini-2.0-flash

    on the same page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     EconPapers
    -0.70
    WebVitals
    -0.60
    WebElementEntity
    -0.57
    Personendaten
    -0.56
    ⓧ
    -0.55
    TableAdapter
    -0.54
    WriteLiteral
    -0.53
    dron
    -0.52
    providedIn
    -0.52
     Lightboxes
    -0.52
    POSITIVE LOGITS
     behalf
    1.27
     basis
    1.23
     occasions
    1.07
     occasion
    1.05
    basis
    0.98
     ועל
    0.93
     grounds
    0.88
     scale
    0.80
     verge
    0.79
     Basis
    0.79
    Activations Density 0.405%

    No Known Activations