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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6748
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or stipulations for participants in programs or services

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

    references to participants and their experiences in programs or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tuur
    -0.46
    englanniksi
    -0.46
     Mansfield
    -0.46
    othes
    -0.45
    atimes
    -0.45
    شک
    -0.45
    longed
    -0.44
     Prise
    -0.44
    åde
    -0.44
    راك
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.83
     automatically
    0.74
    WebElementEntity
    0.69
    getDescriptor
    0.67
    SourceChecksum
    0.65
     nahilalakip
    0.62
    soort
    0.62
    automatically
    0.62
     automaticamente
    0.61
     benefit
    0.61
    Activations Density 0.382%

    No Known Activations