© 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. 13653
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to innocence and rights in judicial contexts

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

    Text after certain punctuation/symbols

    np_acts-logits-general · gemini-2.0-flash

    legal and governmental terms

    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
     Numerade
    -0.52
    <![
    -0.45
    xase
    -0.42
    tonsoft
    -0.42
    whites
    -0.41
     מוצ
    -0.41
    webElement
    -0.41
    IVEREF
    -0.40
    omitempty
    -0.39
    spaghetti
    -0.39
    POSITIVE LOGITS
    enumii
    0.46
    RegressionTest
    0.39
    DBNull
    0.38
    GrantedAuthority
    0.38
     erz
    0.38
    translateX
    0.35
    あまり
    0.35
    AndEndTag
    0.34
     ank
    0.34
     сталь
    0.33
    Activations Density 0.740%

    No Known Activations