© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to functions and analysis

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

    Mathematical or chemical formulas/expressions

    np_acts-logits-general · gemini-2.0-flash

    school-based indirect parental involvement

    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
     <=",
    -0.89
    extAlignment
    -0.87
     Paglinawan
    -0.85
     houſe
    -0.82
    StructEnd
    -0.80
    UnusedPrivate
    -0.78
     CreateTagHelper
    -0.77
     myſelf
    -0.76
    openConnection
    -0.75
     fieldNum
    -0.75
    POSITIVE LOGITS
    rungsseite
    0.56
     COVID
    0.42
    Décès
    0.41
    IRUS
    0.40
     colheres
    0.39
    etCode
    0.38
     Réponses
    0.38
    ında
    0.37
     Menteri
    0.36
     waar
    0.36
    Activations Density 2.744%

    No Known Activations