© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 47013
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "earn" and its associated context

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

    money or accomplishments earned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gridy
    -0.43
    <h1>
    -0.43
    amoja
    -0.42
    ます
    -0.42
    ResultCode
    -0.41
    GroupLayout
    -0.40
    tmpl
    -0.40
     Whittaker
    -0.39
    AtIndex
    -0.39
     Whipple
    -0.39
    POSITIVE LOGITS
    Earn
    0.81
     earn
    0.80
     earns
    0.71
     Earn
    0.68
     earned
    0.68
    earned
    0.66
     Earned
    0.62
    earn
    0.60
     earning
    0.57
    earning
    0.57
    Activations Density 0.009%

    No Known Activations