© 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. 16-GEMMASCOPE-RES-16K
    11. 6786
    Prev
    Next
    INDEX
    Explanations

    conversations or discussions that emphasize legal and judicial processes

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

    Followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    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
    norsk
    -0.57
    ห์
    -0.52
    malıdır
    -0.52
    lunda
    -0.52
    న్ని
    -0.51
    etch
    -0.51
    也可
    -0.51
    volle
    -0.51
    knapp
    -0.51
    kloped
    -0.50
    POSITIVE LOGITS
     really
    0.82
     basically
    0.78
     resourceCulture
    0.78
     somebody
    0.76
     Yeah
    0.70
     kind
    0.70
     actually
    0.69
     very
    0.69
     @"/
    0.68
     Donc
    0.68
    Activations Density 0.185%

    No Known Activations