© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1067
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "fo"

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

    Token "Fo" followed by two more letters

    np_acts-logits-general · gemini-2.0-flash

    foxy, foolish, foamy, foetal, foveal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.54
     createState
    -0.53
    OrCreate
    -0.51
    ▼
    -0.51
    <h6>
    -0.50
    CreateTable
    -0.50
    Attribute
    -0.48
    носи
    -0.47
     Brit
    -0.47
    createServer
    -0.47
    POSITIVE LOGITS
     Roskov
    0.85
     caufe
    0.85
     Jefus
    0.81
     itſelf
    0.79
     poffible
    0.77
     cauſe
    0.76
     Majefty
    0.76
     pleaſure
    0.75
     Fo
    0.75
     myſelf
    0.73
    Activations Density 0.104%

    No Known Activations