© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting elements

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

    repetitive formatting elements or stylistic choices in a text

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

    tokens after asterisk

    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
    — 
    -0.71
     ویکی‌پدی
    -0.67
     betweenstory
    -0.66
    enerys
    -0.65
    AccessorTable
    -0.64
    клопе
    -0.63
    doria
    -0.61
     CreateTagHelper
    -0.60
     ――
    -0.59
    Œuvres
    -0.59
    POSITIVE LOGITS
     Prev
    0.60
     CanadaChoose
    0.58
     Share
    0.51
     prev
    0.49
    Prev
    0.47
    prev
    0.47
    mybatisplus
    0.47
    勃
    0.46
    AutoScaleMode
    0.46
    orb
    0.46
    Activations Density 0.042%

    No Known Activations