© 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. 18-GEMMASCOPE-RES-16K
    11. 8866
    Prev
    Next
    INDEX
    Explanations

    visibility modifiers in class definitions

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

    Code, class, or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    public class, better option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RequestOptions
    -0.53
     '').
    -0.47
     atve
    -0.47
     visione
    -0.47
    ()?;
    -0.47
     '');
    -0.47
     cappello
    -0.45
     senare
    -0.45
     pidana
    -0.45
     "");
    -0.45
    POSITIVE LOGITS
     متعلقه
    0.87
     AssemblyTitle
    0.82
    ագրություններ
    0.80
    rungsseite
    0.78
    مصادر
    0.77
    #+#
    0.73
     snippetHide
    0.70
    Autoritní
    0.70
    Erreferentziak
    0.69
    WebServlet
    0.68
    Activations Density 0.009%

    No Known Activations