Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12147
    Prev
    Next
    INDEX
    Explanations

    numeric patterns or sequences in data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uldade
    -0.48
    omenclature
    -0.47
     dür
    -0.46
    ropolitana
    -0.46
    foreignKey
    -0.44
    msgid
    -0.44
    opardy
    -0.44
     >::
    -0.44
    prilis
    -0.43
    MigrationBuilder
    -0.42
    POSITIVE LOGITS
     EconPapers
    0.90
    enderror
    0.68
    CloseOperation
    0.67
     يتيمه
    0.66
    databind
    0.66
    
    0.64
    ยว
    0.62
     HasFactory
    0.60
    بوابة
    0.58
     ligiloj
    0.56
    Activations Density 0.572%

    No Known Activations