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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9723
    Prev
    Next
    INDEX
    Explanations

    declarative statements about required fields in a data structure or API response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "?>
    -0.62
    UVWXYZ
    -0.61
    /-/
    -0.59
    iolis
    -0.56
    |--
    -0.56
    ielli
    -0.55
    PointerException
    -0.53
     Gandalf
    -0.53
    IMM
    -0.53
    Penulis
    -0.51
    POSITIVE LOGITS
    /"
    0.83
    /'
    0.72
    /";
    0.67
    ="<?=
    0.62
    تقاوى
    0.57
    endregion
    0.57
    <thead>
    0.57
     Margot
    0.56
    /");
    0.56
    GEBURTSDATUM
    0.56
    Activations Density 0.048%

    No Known Activations