© 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. 1580
    Prev
    Next
    INDEX
    Explanations

    references to academic authors and their contributions

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

    introducing a summary or reminder

    np_acts-logits-general · gemini-2.0-flash

    proofs and outlines

    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
     katanya
    -0.54
    LikeLike
    -0.51
     autorytatywna
    -0.44
    呢
    -0.42
    ientí
    -0.42
    啊
    -0.41
    nyata
    -0.41
    عن
    -0.40
    …
    -0.40
     mierda
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.95
     briefly
    0.94
     brevity
    0.93
     Readers
    0.83
    )");
    0.78
     brevemente
    0.76
     digress
    0.76
     subsections
    0.75
    }));
    0.74
    abestanden
    0.73
    Activations Density 1.290%

    No Known Activations