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. 1-GEMMASCOPE-RES-16K
    6. 7764
    Prev
    Next
    INDEX
    Explanations

    phrases or words that indicate a contrast or separation from a main idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.63
    ьаж
    -0.60
    %");
    -0.56
    ."],
    -0.54
     resulting
    -0.53
    haviour
    -0.53
     bucket
    -0.52
    TextUtils
    -0.52
    //};
    -0.51
    ennifer
    -0.51
    POSITIVE LOGITS
     aside
    0.90
    ArgsConstructor
    0.85
     Indonesia
    0.70
     collè
    0.68
    WriteLiteral
    0.68
     enfans
    0.67
     AssemblyCompany
    0.66
     assise
    0.66
     deleteById
    0.65
     espagnole
    0.64
    Activations Density 0.076%

    No Known Activations