Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81151
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethical dilemmas and the implications of decisions

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

    possibility and future 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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     '\\;'
    -0.39
     want
    -0.35
    sieur
    -0.33
     nac
    -0.32
    Objetivos
    -0.32
    charCode
    -0.32
    fillable
    -0.31
    CardHeader
    -0.30
     inca
    -0.30
     onCreateView
    -0.30
    POSITIVE LOGITS
    الإنجليزية
    0.66
     puder
    0.53
     useAppContext
    0.49
    
    0.48
    
    0.47
    رشف
    0.46
    qrstuvwxyz
    0.45
    المناصب
    0.44
     einsch
    0.43
    rebbe
    0.43
    Activations Density 0.132%

    No Known Activations