© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    specific structure or patterns in data, particularly those related to file paths or URLs

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

    Tokens after forward slash

    np_acts-logits-general · gemini-2.0-flash

    / followed by text

    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
     ſind
    -0.68
     dezelve
    -0.60
     Anſ
    -0.58
     feroit
    -0.56
     plufieurs
    -0.54
     pouvoit
    -0.53
     Houſe
    -0.52
     iſt
    -0.51
    Datuak
    -0.51
     enfans
    -0.50
    POSITIVE LOGITS
    /
    1.45
     /
    1.27
    {}/
    1.14
    ()/
    1.13
    |/
    1.13
    -/
    1.06
    }/
    1.05
    ／
    1.03
    ]/
    1.02
    %/
    1.01
    Activations Density 0.405%

    No Known Activations