© 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. 24-GEMMASCOPE-RES-16K
    11. 13809
    Prev
    Next
    INDEX
    Explanations

    comparative and numerical information in contexts involving evaluations or assessments

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

    legal citations

    np_acts-logits-general · gemini-2.0-flash

    Swift project, Maven artifacts

    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
    bolistas
    -0.53
    Referencias
    -0.49
    albero
    -0.47
    ·
    -0.47
     Taktlose
    -0.46
    ánicas
    -0.44
    -0.43
    quiao
    -0.42
    &&&&
    -0.42
    toHaveBeenCalled
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.84
     متعلقه
    0.76
     preco
    0.70
     oregon
    0.69
     онъ
    0.68
     arsenic
    0.67
     helium
    0.65
     successful
    0.62
     beaute
    0.62
     perchance
    0.62
    Activations Density 0.055%

    No Known Activations