© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4342
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly focusing on nieces and nephews

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

    Family relationships

    np_acts-logits-general · gemini-2.0-flash

    aunts, uncles, nieces, nephews

    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
    aarrggbb
    -0.54
    WindowConstants
    -0.52
     defaultstate
    -0.47
    MemoryWarning
    -0.45
    strSql
    -0.44
    addCriterion
    -0.43
     oprot
    -0.41
    providedIn
    -0.41
     dragón
    -0.40
    KommentareTeilen
    -0.38
    POSITIVE LOGITS
     nephews
    0.81
     nieces
    0.74
     nephew
    0.73
    aspectj
    0.64
     cousin
    0.63
     niece
    0.62
     cousins
    0.61
     uncle
    0.61
     Uncle
    0.60
    uncle
    0.59
    Activations Density 0.040%

    No Known Activations