Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8796
    Prev
    Next
    INDEX
    Explanations

    questions or phrases expressing confusion or inquiry about current situations

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

    Questions about a situation

    np_acts-logits-general · gemini-2.0-flash

    what's going on

    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
    MigrationBuilder
    -0.71
    AsUp
    -0.67
     Kante
    -0.62
    pade
    -0.57
    uchtet
    -0.57
     Euph
    -0.55
    zką
    -0.54
    +#+
    -0.53
     Huguen
    -0.53
    UKO
    -0.52
    POSITIVE LOGITS
     happening
    1.22
     happened
    0.98
     Happening
    0.96
     what
    0.95
     happenings
    0.85
     whats
    0.85
     occurring
    0.85
     occurred
    0.81
    happened
    0.80
     happen
    0.79
    Activations Density 0.129%

    No Known Activations