© 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. 8974
    Prev
    Next
    INDEX
    Explanations

    sequences of special characters and punctuation

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

    Text separated by many spaces

    np_acts-logits-general · gemini-2.0-flash

    special characters or formatting

    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
    يكب
    -0.88
    Personendaten
    -0.84
    TypedDataSet
    -0.83
    tagHelperRunner
    -0.79
     témoig
    -0.78
     queſta
    -0.77
    adaptiveStyles
    -0.75
     كومونز
    -0.75
    ésultats
    -0.73
     typelib
    -0.73
    POSITIVE LOGITS
     
    0.51
    ↵↵
    0.48
    ↵
    0.46
    ing
    0.41
    <strong>
    0.41
    :
    0.41
     all
    0.41
    ist
    0.41
    1
    0.40
    //
    0.39
    Activations Density 0.653%

    No Known Activations