© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4546
    Prev
    Next
    INDEX
    Explanations

    documents with a diverse range of subject matter, indicating no specific thematic activation

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

    Appears before a number or special character

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    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
    脚注の使い方
    -0.60
    felf
    -0.56
    IsMutable
    -0.56
     poffible
    -0.55
    ResumeLayout
    -0.54
    mier
    -0.52
    felves
    -0.52
    PyExc
    -0.51
     Majefty
    -0.51
    ſelf
    -0.51
    POSITIVE LOGITS
    ftagPool
    0.76
     it
    0.76
    bootstrapcdn
    0.70
     nawr
    0.65
    帖最后由
    0.62
     oprot
    0.60
     JUGA
    0.60
    StoryboardSegue
    0.59
    ScopeManager
    0.57
     оно
    0.55
    Activations Density 0.035%

    No Known Activations