© 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. 0-GEMMASCOPE-RES-16K
    11. 3048
    Prev
    Next
    INDEX
    Explanations

    the concept of avoiding negative outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Stit
    -0.50
     Refin
    -0.50
    oa̍t
    -0.49
     sou
    -0.48
     paste
    -0.48
    Sou
    -0.48
    PARATUS
    -0.48
     tourmaline
    -0.46
    delwed
    -0.46
     camar
    -0.46
    POSITIVE LOGITS
     Avoid
    0.60
    Avoid
    0.59
     avoided
    0.57
     avoiding
    0.54
     avoid
    0.54
    avoid
    0.54
     avoids
    0.49
     Avoiding
    0.48
     pit
    0.47
     navideña
    0.45
    Activations Density 0.212%

    No Known Activations