© 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. 19-GEMMASCOPE-RES-16K
    11. 12100
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate decision-making or taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.81
    hyrchwyd
    -0.78
    oredCriteria
    -0.76
    省市镇
    -0.67
    expandindo
    -0.65
    SerializedName
    -0.65
    nodoc
    -0.63
    ukone
    -0.62
    XtraGrid
    -0.62
    WithIOException
    -0.61
    POSITIVE LOGITS
     undertake
    1.28
     undertaking
    1.27
     challenge
    1.26
     tackled
    1.19
     undertook
    1.17
     undertakes
    1.14
     undertaken
    1.14
     tackling
    1.14
    challenge
    1.12
     tackle
    1.11
    Activations Density 0.293%

    No Known Activations