© 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. 22-GEMMASCOPE-RES-16K
    11. 5775
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols within text

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

    Follows a period or ellipsis

    np_acts-logits-general · gemini-2.0-flash

    slot machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.67
    djangoproject
    -0.55
    libft
    -0.52
    webElementXpaths
    -0.51
    ɵɵ
    -0.51
    encodeWith
    -0.48
    opsida
    -0.47
    XMLSchema
    -0.45
    IsMutable
    -0.45
    nsito
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.77
    WaitGroup
    0.74
     AssemblyTitle
    0.73
     وتسجيلات
    0.65
     Daarom
    0.64
     kasarigan
    0.64
     nobody
    0.63
    unlike
    0.63
     Ảnh
    0.62
     pinulongan
    0.62
    Activations Density 0.264%

    No Known Activations