© 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. 418
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries regarding understanding and knowledge

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

    Questions starting with "how," "why," "what," "when," etc

    np_acts-logits-general · gemini-2.0-flash

    question words and how

    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
    ضم
    -0.44
    faf
    -0.44
    Personensuche
    -0.43
     relief
    -0.42
    nocache
    -0.42
     Formerly
    -0.41
    hella
    -0.41
    rawdę
    -0.41
    faits
    -0.41
    Rourke
    -0.40
    POSITIVE LOGITS
     what
    1.38
     how
    1.27
     why
    1.19
    what
    1.06
     where
    1.04
     What
    0.95
    What
    0.92
    why
    0.92
     whom
    0.90
     WHAT
    0.88
    Activations Density 0.279%

    No Known Activations