© 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. 52984
    Prev
    Next
    INDEX
    Explanations

    references to the number three or its variations in different contexts

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

    the ordinal third

    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
     alluminio
    -0.42
     wą
    -0.42
    enciais
    -0.38
     począ
    -0.38
     kés
    -0.38
     gesteld
    -0.36
     bepaald
    -0.36
     aislada
    -0.36
    zok
    -0.36
    olden
    -0.35
    POSITIVE LOGITS
     Third
    0.93
     third
    0.93
    Third
    0.92
    third
    0.88
     THIRD
    0.86
    THIRD
    0.84
     Thirdly
    0.79
    цездатний
    0.76
    adaptiveStyles
    0.73
     troisième
    0.73
    Activations Density 0.251%

    No Known Activations