© 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. 3967
    Prev
    Next
    INDEX
    Explanations

    references to specific species and their classifications

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

    after punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    species names and technical terms

    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
    COR
    -0.45
     cor
    -0.43
    anci
    -0.42
     emp
    -0.42
     plus
    -0.42
    hip
    -0.41
     Wal
    -0.41
    位
    -0.41
    plus
    -0.40
     sla
    -0.40
    POSITIVE LOGITS
     ویکی‌پدیا
    0.95
     Roskov
    0.87
     BoxFit
    0.79
    AddHtmlAttribute
    0.76
     blest
    0.73
    AxisAlignment
    0.73
     cavitation
    0.73
    XmlAccessorType
    0.72
    HtmlAttribute
    0.72
    nonatomic
    0.72
    Activations Density 0.151%

    No Known Activations