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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8630
    Prev
    Next
    INDEX
    Explanations

    specific programming terms and elements related to data structures and functions

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

    Tokens within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    advance_backward, module, MODE, call

    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
    "])
    
    -0.58
    "]);
    
    -0.55
     imp
    -0.53
    /******/
    -0.52
    teln
    -0.52
    orney
    -0.51
    ANCIAL
    -0.51
    FORMAN
    -0.49
     năng
    -0.49
    "],
    
    -0.48
    POSITIVE LOGITS
     الرياضيه
    0.73
    IntoConstraints
    0.67
     hjäl
    0.66
    :+:
    0.62
     Allí
    0.57
    extAlignment
    0.56
     xenia
    0.56
     itſelf
    0.56
     Molière
    0.55
     Abbé
    0.55
    Activations Density 1.346%

    No Known Activations