© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14633
    Prev
    Next
    INDEX
    Explanations

    themes related to rescue and saving lives

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

    phrases involving heroic rescue or saving someone/something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Versammlung
    -0.41
     casó
    -0.36
     correspond
    -0.35
    BSITE
    -0.35
    medad
    -0.35
    慣
    -0.34
    COMMIT
    -0.34
     positive
    -0.33
     gustaba
    -0.32
     plă
    -0.32
    POSITIVE LOGITS
     rescue
    1.24
     rescuing
    1.15
     rescued
    1.15
    rescue
    1.09
    Rescue
    1.07
     rescues
    1.05
     Rescue
    1.03
     Rettung
    0.98
     rescu
    0.97
    rescu
    0.96
    Activations Density 0.150%

    No Known Activations