© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4027
    Prev
    Next
    INDEX
    Explanations

    references to grant numbers and academic funding sources

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

    Initials followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    grant and citation codes

    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
     nahilalakip
    -0.93
    MigrationBuilder
    -0.91
     дописавши
    -0.85
    IVEREF
    -0.74
     désolés
    -0.74
    setVerticalGroup
    -0.73
     للمعارف
    -0.71
    bootstrapcdn
    -0.70
     lenker
    -0.69
    GraphicsUnit
    -0.69
    POSITIVE LOGITS
    eleste
    0.57
     betweenstory
    0.52
     Mauritania
    0.46
     Ananda
    0.45
    cidas
    0.44
    pagnol
    0.44
     Judea
    0.44
    opatra
    0.44
     Deuteronomy
    0.43
    nyv
    0.43
    Activations Density 1.025%

    No Known Activations