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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1033
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes related to web page structure

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

    Followed by "except"

    np_acts-logits-general · gemini-2.0-flash

    except in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.32
     Theſe
    -0.31
    ideration
    -0.29
    tonode
    -0.29
    drawal
    -0.28
     Efq
    -0.28
     дії
    -0.28
    csolódó
    -0.28
     חיצוני
    -0.27
     whoſe
    -0.27
    POSITIVE LOGITS
    <bos>
    1.17
     queſta
    0.39
    
    0.36
    MathML
    0.35
     allAfrica
    0.35
    ер
    0.35
    ρυ
    0.35
    Clik
    0.34
    例文帳に追加
    0.34
    はじめに
    0.33
    Activations Density 53.114%

    No Known Activations