© 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. 16-GEMMASCOPE-RES-16K
    11. 6804
    Prev
    Next
    INDEX
    Explanations

    references to German language or culture, particularly in legal or historical contexts

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

    Text inside quotation marks or brackets

    np_acts-logits-general · gemini-2.0-flash

    [sic] citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \$
    -0.63
    IVEREF
    -0.61
    KommentareTeilen
    -0.60
     незавершена
    -0.59
     دیکھیے
    -0.58
     $\$
    -0.55
    μως
    -0.52
    offsetWidth
    -0.51
    showConfirm
    -0.51
    rimônio
    -0.50
    POSITIVE LOGITS
    <em>
    1.87
    <i>
    1.76
    <code>
    1.04
     /*
    0.97
    """
    0.85
    /*
    0.84
     `
    0.73
    <u>
    0.73
    """
    0.71
    /*
    0.71
    Activations Density 0.155%

    No Known Activations