© 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. 336
    Prev
    Next
    INDEX
    Explanations

    terms related to time, particularly the concept of "ever."

    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
    setVerticalGroup
    -0.73
    SharedDtor
    -0.70
    WriteLiteral
    -0.58
     équi
    -0.56
     always
    -0.55
    Always
    -0.55
    URLException
    -0.54
    AsUp
    -0.54
     IndexPath
    -0.54
     InputDecoration
    -0.53
    POSITIVE LOGITS
    greens
    0.87
    lasting
    0.84
    present
    0.77
    last
    0.69
    glades
    0.69
     present
    0.65
     widening
    0.65
     increasing
    0.64
    THING
    0.63
    LAST
    0.62
    Activations Density 0.134%

    No Known Activations