© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 40
    Prev
    Next
    INDEX
    Explanations

    nuanced approaches to problem-solving in various contexts

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

    phrases that indicate a candid or direct approach to personal circumstances

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

    different approach

    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
    AutoField
    -0.56
     Preferencias
    -0.53
    ünsche
    -0.52
    tableFuture
    -0.50
    TargetException
    -0.50
    íqu
    -0.50
    useEffect
    -0.49
    nict
    -0.49
    tiéndose
    -0.49
    ᵕ
    -0.49
    POSITIVE LOGITS
     approach
    2.94
     Approach
    2.54
    approach
    2.53
     APPROACH
    2.36
    Approach
    2.31
     approche
    2.26
     approaches
    2.14
     abordagem
    2.02
    approche
    2.02
     approached
    1.95
    Activations Density 0.238%

    No Known Activations