© 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. 3-GEMMASCOPE-RES-16K
    11. 12563
    Prev
    Next
    INDEX
    Explanations

    structured data representations, especially in tabular form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.68
    Tikang
    -0.64
    脚注の使い方
    -0.58
     оригіналу
    -0.57
     Baillargeon
    -0.56
    dropna
    -0.56
    WebServlet
    -0.53
     referrerpolicy
    -0.52
    enumii
    -0.51
    MLLoader
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.56
    الإنجليزية
    0.55
    //
    0.54
    DataColumn
    0.54
     pyrolysis
    0.54
     aussehen
    0.53
    WillAppear
    0.53
    flare
    0.52
    amet
    0.52
    NewRow
    0.52
    Activations Density 0.585%

    No Known Activations