© 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. 24-GEMMASCOPE-RES-16K
    6. 6421
    Prev
    Next
    INDEX
    Explanations

    references to legal or financial concepts related to tax-related issues

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

    followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.50
    
    -0.45
    DIPSETTING
    -0.45
    antMatchers
    -0.45
     typelib
    -0.45
     NSCoder
    -0.44
    Erreferentziak
    -0.41
    demás
    -0.41
     lenker
    -0.41
     referência
    -0.41
    POSITIVE LOGITS
     &___
    0.45
    )];
    
    0.43
    cloak
    0.40
    bufio
    0.39
    versible
    0.39
    cratic
    0.39
     GNA
    0.38
    ejb
    0.38
     HAP
    0.38
    hairs
    0.38
    Activations Density 0.791%

    No Known Activations