© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    references to the name "Tom"

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

    The token "Tom"

    np_acts-logits-general · gemini-2.0-flash

    Tom followed by names

    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
    extra
    -0.50
    RESUMO
    -0.49
    itinéraire
    -0.48
    GOTREF
    -0.47
    ire
    -0.47
    重
    -0.45
     تانيه
    -0.45
     extra
    -0.45
     AssemblyCulture
    -0.45
    SerializedName
    -0.44
    POSITIVE LOGITS
    esModule
    0.70
    
    0.68
     }}"></
    0.60
    TargetException
    0.58
    kloped
    0.58
     linkovi
    0.58
    linson
    0.57
     AssemblyTitle
    0.57
    terday
    0.56
     Hanks
    0.56
    Activations Density 0.127%

    No Known Activations