© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1508
    Prev
    Next
    INDEX
    Explanations

    capabilities and skills related to practical tasks

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

    negative phrasing and words that indicate inability or denial

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

    can followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    writeFieldEnd
    -0.54
     tentar
    -0.54
    tryk
    -0.53
    ReusableCell
    -0.51
    try
    -0.49
     tentativa
    -0.48
     essais
    -0.48
     try
    -0.47
     proberen
    -0.47
     tentativo
    -0.46
    POSITIVE LOGITS
     handle
    0.71
    handle
    0.64
     tå
    0.63
    handles
    0.62
    ]--;
    0.61
     handles
    0.61
    featureID
    0.60
     Handle
    0.60
    BSITE
    0.59
    SharedCtor
    0.59
    Activations Density 0.093%

    No Known Activations