© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14296
    Prev
    Next
    INDEX
    Explanations

    legal language and terms related to conditions and exceptions

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

    Punctuation (, or )) followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    punctuation and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     düş
    -0.35
    providedIn
    -0.34
    line
    -0.33
    JsonIgnore
    -0.33
    gra
    -0.33
     ση
    -0.32
    andas
    -0.32
     conoc
    -0.32
    emed
    -0.32
     vorn
    -0.32
    POSITIVE LOGITS
    tanleria
    0.69
     deſt
    0.61
     houſe
    0.60
     faſt
    0.58
     raiſ
    0.58
     juſ
    0.56
     canst
    0.54
     fevere
    0.54
     ſta
    0.54
     auffi
    0.53
    Activations Density 0.543%

    No Known Activations