© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1491
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial or statistical values

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

    numerical values and statistical references related to events and entities

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

    scientific notation or hexadecimal numbers

    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
     estekak
    -0.86
    __":
    -0.85
     فريبيس
    -0.81
     Drapeau
    -0.80
    Datuak
    -0.80
     يتيمه
    -0.79
     étoient
    -0.77
    onAttach
    -0.77
    /**
    -0.76
     كومونز
    -0.76
    POSITIVE LOGITS
     
    0.59
     O
    0.56
     I
    0.49
     c
    0.48
     et
    0.45
     Z
    0.45
     on
    0.44
     or
    0.44
     in
    0.42
     E
    0.42
    Activations Density 0.152%

    No Known Activations