© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9029
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rescue" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.96
    parsedMessage
    -0.94
     %>%
    -0.91
    SourceChecksum
    -0.91
     ब्रेकडाउन
    -0.90
    ThroughAttribute
    -0.89
     craindre
    -0.88
    GEBURTSDATUM
    -0.87
    brtc
    -0.86
     Lightboxes
    -0.83
    POSITIVE LOGITS
     Bro
    0.70
    c
    0.65
     rescue
    0.61
     Rescue
    0.57
     deep
    0.49
     Brother
    0.49
     Technology
    0.49
     Government
    0.49
    tal
    0.48
    Bro
    0.48
    Activations Density 0.212%

    No Known Activations