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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 3982
    Prev
    Next
    INDEX
    Explanations

    sentiments related to obligation and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -0.57
    ”
    -0.52
    Scaler
    -0.47
     لكرة
    -0.46
     droits
    -0.42
     [
    -0.42
    .”
    -0.42
     territoire
    -0.39
    </em>
    -0.39
    “
    -0.39
    POSITIVE LOGITS
    ValueStyle
    1.10
    SourceChecksum
    1.03
    rungsseite
    0.93
    脚注の使い方
    0.92
    RunAsync
    0.87
     <<<<<<<<<<<<<<
    0.86
    Manbalar
    0.83
    makeConstraints
    0.83
    tagHelperRunner
    0.83
     חיצוניים
    0.82
    Activations Density 0.468%

    No Known Activations