© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6774
    Prev
    Next
    INDEX
    Explanations

    expressions related to taking risks and embracing new experiences

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

    Risk-taking and bravery

    np_acts-logits-general · gemini-2.0-flash

    daring and taking chances

    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
     disambiguazione
    -0.64
    GOTREF
    -0.63
    exitRule
    -0.59
    曖昧さ回避
    -0.59
     Efq
    -0.53
     zwiſchen
    -0.52
     Dieſe
    -0.52
    ChildScrollView
    -0.51
    <pad>
    -0.50
    [@BOS@]
    -0.50
    POSITIVE LOGITS
     daring
    0.86
     risky
    0.82
     bold
    0.80
     boldly
    0.79
     courageous
    0.75
     venture
    0.73
     arries
    0.71
     brave
    0.70
     adventurous
    0.69
     risk
    0.69
    Activations Density 0.288%

    No Known Activations