© 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. 20-GEMMASCOPE-RES-131K
    11. 50712
    Prev
    Next
    INDEX
    Explanations

    references to rarity and uniqueness in collectible items, particularly cars

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

    rarity and uncommon things

    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
    GEBURTSDATUM
    -0.64
     betweenstory
    -0.53
    HasAnnotation
    -0.53
    
    -0.52
     snippetHide
    -0.50
    KURZBESCHREIBUNG
    -0.50
    findpost
    -0.48
    ConstraintMaker
    -0.47
     ModelRenderer
    -0.45
    tanleria
    -0.45
    POSITIVE LOGITS
     rare
    0.52
     rarer
    0.52
     Rare
    0.48
    Rare
    0.47
     RARE
    0.42
     rarest
    0.42
     rarity
    0.41
     selten
    0.39
    VersionUID
    0.39
    难得
    0.39
    Activations Density 0.006%

    No Known Activations