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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5372
    Prev
    Next
    INDEX
    Explanations

    names of individuals and entities associated with various contexts

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

    Tokens followed by verbs of saying or production

    np_acts-logits-general · gemini-2.0-flash

    names followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.56
    ";
    -0.47
     serem
    -0.46
     }.
    -0.46
     économies
    -0.44
    ".
    -0.44
    .";
    -0.44
     podendo
    -0.44
     kuin
    -0.43
     ilman
    -0.43
    POSITIVE LOGITS
     told
    1.46
     took
    1.43
     gave
    1.43
     said
    1.42
     had
    1.42
     wrote
    1.39
     was
    1.39
     asked
    1.36
     began
    1.36
     went
    1.34
    Activations Density 1.296%

    No Known Activations