© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 807
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with risk and caution

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

    Avoidance of negative outcomes

    np_acts-logits-general · gemini-2.0-flash

    avoiding negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     HasFactory
    -0.79
    :✨
    -0.72
    AsUp
    -0.71
    ArgsConstructor
    -0.69
    ########.
    -0.67
     invokingState
    -0.65
     kasarigan
    -0.63
     queſta
    -0.60
     CanadaChoose
    -0.60
    новниш
    -0.59
    POSITIVE LOGITS
     losing
    0.53
     lose
    0.51
     risk
    0.50
     loss
    0.47
     perder
    0.44
     mis
    0.42
     RISK
    0.41
     loosing
    0.41
     avoid
    0.41
    risk
    0.38
    Activations Density 0.232%

    No Known Activations