© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 642
    Prev
    Next
    INDEX
    Explanations

    occurrences of the token "sho" and its variations

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

    occurrences of the word "sho."

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

    words starting with sho

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    WebVitals
    -1.03
    rungsseite
    -0.81
    GEBURTSDATUM
    -0.78
    astify
    -0.75
    XmlEnum
    -0.75
    Datuak
    -0.73
    #+#
    -0.73
    曖昧さ回避
    -0.72
    GIH
    -0.72
    IVEREF
    -0.71
    POSITIVE LOGITS
     Sho
    1.01
    Sho
    0.97
    sho
    0.84
     sho
    0.81
     SHO
    0.59
    SHO
    0.57
    Scho
    0.53
     Shovel
    0.49
     zask
    0.48
     Шо
    0.47
    Activations Density 0.014%

    No Known Activations