© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14186
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific names, roles, or designations in legal and professional contexts

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

    possessive apostrophes in proper names (surnames followed by 's).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    possessive forms of proper nouns (names followed by apostrophes).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    named entities, especially proper nouns like people, organizations, places, and titles.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.42
     (
    -0.38
    ,
    -0.36
     ‘
    -0.35
    方は
    -0.34
      
    -0.34
    ↵
    -0.33
     
    -0.33
     ('
    -0.33
    りは
    -0.33
    POSITIVE LOGITS
    ’
    1.15
    $'
    0.99
    '
    0.96
    Билгалдахарш
    0.84
    ův
    0.84
    ChildScrollView
    0.84
    ningens
    0.79
     queſta
    0.78
     surla
    0.76
    IntoConstraints
    0.75
    Activations Density 2.139%

    No Known Activations