© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6794
    Prev
    Next
    INDEX
    Explanations

    structured data and programming terminology related to configuration and attributes

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

    strings of code or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.53
     přev
    -0.52
    onshire
    -0.51
     Cipri
    -0.49
    輻
    -0.49
     GEAR
    -0.46
    WireFormatLite
    -0.46
     مرئيه
    -0.46
    χρι
    -0.46
    >),
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.73
    tvguidetime
    0.69
    endpush
    0.63
    StructEnd
    0.63
    oredCriteria
    0.62
    Välislingid
    0.60
    Viitteet
    0.60
    ItemBackground
    0.60
    ----</
    0.59
    propTypes
    0.59
    Activations Density 1.994%

    No Known Activations