© 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. 1-GEMMASCOPE-RES-16K
    11. 5904
    Prev
    Next
    INDEX
    Explanations

    phrases urging the reader to recall important information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recalling
    -0.74
     recalls
    -0.73
     recalled
    -0.66
     recall
    -0.61
     flashbacks
    -0.60
    FileChooser
    -0.60
     cilia
    -0.57
     Acorn
    -0.56
     recollections
    -0.55
    شع
    -0.55
    POSITIVE LOGITS
     שוליים
    0.80
     Ja
    0.75
     للمعارف
    0.72
    payload
    0.71
     payload
    0.71
    SourceChecksum
    0.71
     MainAxisSize
    0.68
     виправивши
    0.66
    __((
    0.64
    XMLSchema
    0.63
    Activations Density 0.080%

    No Known Activations