© 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. 712
    Prev
    Next
    INDEX
    Explanations

    the sequences of letters "ath" and "ith" appearing in various words

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

    the word "Ath" and variations of "th"

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

    Dithmarschen

    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
     CreateTagHelper
    -0.97
     وتسجيلات
    -0.64
    TagHelper
    -0.61
    期刊论文
    -0.61
    Brainz
    -0.60
    ModelAdmin
    -0.60
    teryx
    -0.57
    ✨:
    -0.57
    ougars
    -0.57
     Cougars
    -0.55
    POSITIVE LOGITS
    archiviato
    0.54
    ⓧ
    0.49
    Ouch
    0.48
    зап
    0.45
    uth
    0.44
     Expedia
    0.44
    wechs
    0.44
    UIControlState
    0.43
    any
    0.43
     Inet
    0.43
    Activations Density 0.054%

    No Known Activations