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. 1392
    Prev
    Next
    INDEX
    Explanations

    keywords related to operational conditions or states in software or experimental contexts

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

    "presence of" or related words

    np_acts-logits-general · gemini-2.0-flash

    presence of or and

    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
    出版年
    -0.80
     utafitiHapana
    -0.71
    脚注の使い方
    -0.70
    RenderAtEndOf
    -0.69
     Мексичка
    -0.69
     ContentValues
    -0.68
     jLabel
    -0.67
    <%@
    -0.67
    IsContent
    -0.66
    cplusplus
    -0.65
    POSITIVE LOGITS
     or
    1.68
     или
    1.30
    或
    1.16
     maupun
    1.14
     atau
    1.10
    /
    1.06
    หรือ
    1.06
     یا
    1.05
     eller
    1.04
     ataupun
    1.03
    Activations Density 0.645%

    No Known Activations