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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12127
    Prev
    Next
    INDEX
    Explanations

    identifiers and parameters relevant to computing or data processing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depending
    -0.48
    єн
    -0.46
     bỏng
    -0.46
     most
    -0.46
     indirectly
    -0.45
     unplanned
    -0.44
    ロール
    -0.43
    ChildIndex
    -0.43
     MenuView
    -0.43
    pressor
    -0.42
    POSITIVE LOGITS
    UserScript
    1.09
    <bos>
    0.90
     Autorizaciones
    0.83
     незавершена
    0.81
    出版年
    0.80
    fjspx
    0.80
    extAlignment
    0.79
    脚注の使い方
    0.78
     ویکی‌پدیا
    0.76
     getItemId
    0.70
    Activations Density 0.624%

    No Known Activations