© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

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

    URLs starting with "https://"

    np_acts-logits-general · gemini-2.0-flash

    protocol delimiters in urls

    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
    ReusableCell
    -0.67
     propOrder
    -0.58
     ddelweddau
    -0.56
    postsleuth
    -0.55
    VELAND
    -0.54
     InputDecoration
    -0.53
    pushFollow
    -0.53
    insee
    -0.52
    
    -0.52
    gestone
    -0.51
    POSITIVE LOGITS
    www
    1.60
    ://
    1.43
     www
    1.21
    ://"
    0.84
    youtu
    0.77
    Www
    0.75
    WWW
    0.69
    ="//
    0.65
    tinyurl
    0.62
    github
    0.60
    Activations Density 0.056%

    No Known Activations