© 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. 8262
    Prev
    Next
    INDEX
    Explanations

    code structures and their associated methods or properties

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

    Code and variable names

    np_acts-logits-general · gemini-2.0-flash

    code within methods

    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
     announcement
    -0.83
     announcing
    -0.72
     announced
    -0.71
     announcements
    -0.67
     announces
    -0.63
     announce
    -0.60
     Announcement
    -0.58
     annon
    -0.56
    ANNOUNC
    -0.54
    ann
    -0.54
    POSITIVE LOGITS
    sizeCache
    0.96
     _
    0.89
    InjectAttribute
    0.87
     &___
    0.79
    ​—
    0.76
    m
    0.74
     Shakspeare
    0.73
    
    0.73
    fjspx
    0.73
     m
    0.73
    Activations Density 0.240%

    No Known Activations