© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    references to links and connections

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

    The token "link" or "links"

    np_acts-logits-general · gemini-2.0-flash

    hyperlinks and connections

    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
    ArgsConstructor
    -0.87
     BoxDecoration
    -0.78
     שוליים
    -0.71
    큼
    -0.71
     SRT
    -0.69
     EdgeInsets
    -0.68
    帖最后由
    -0.67
     InputDecoration
    -0.67
    spesies
    -0.66
    +};
    -0.64
    POSITIVE LOGITS
     LINK
    1.17
     Link
    1.10
     link
    1.08
    links
    1.08
     links
    1.07
     Links
    1.03
    LINK
    1.00
    Links
    0.99
    link
    0.99
     LINKS
    0.97
    Activations Density 0.128%

    No Known Activations