© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13376
    Prev
    Next
    INDEX
    Explanations

    content related to software drivers and their downloads

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

    Followed by "we," "in," or a URL

    np_acts-logits-general · gemini-2.0-flash

    website and content descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.63
    undering
    -0.55
     defStyle
    -0.48
     subscriptions
    -0.45
    essage
    -0.44
    RetentionPolicy
    -0.44
    водство
    -0.42
    льников
    -0.42
    TLDR
    -0.41
    omeness
    -0.41
    POSITIVE LOGITS
    )");
    0.81
     للاسماء
    0.81
    ."));
    0.76
    )}</
    0.76
    VYMaps
    0.76
    الإنجليزية
    0.72
     مرئيه
    0.72
    rungsseite
    0.72
    !")
    0.71
    )"),
    0.70
    Activations Density 0.110%

    No Known Activations