© 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. 10-GEMMASCOPE-RES-16K
    11. 4276
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...");
    -0.59
    %@",
    -0.57
    jerg
    -0.57
    outre
    -0.56
    )";
    -0.55
     Cuban
    -0.54
    de
    -0.54
    getAttributes
    -0.54
    ite
    -0.54
     Rote
    -0.53
    POSITIVE LOGITS
    DeleteCommand
    0.82
    saraba
    0.81
    AddTagHelper
    0.81
     auroit
    0.80
    GHIJKLM
    0.79
    TagHelper
    0.79
     avoient
    0.77
     feroit
    0.76
     hiér
    0.74
     تانيه
    0.74
    Activations Density 0.277%

    No Known Activations