© 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
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6332
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to dominant variables in statistical contexts, specifically focusing on letter combinations and probabilistic assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izon
    -0.53
    RTSC
    -0.52
    慨
    -0.51
     CEA
    -0.51
    VOA
    -0.50
     Farrell
    -0.48
    HEA
    -0.47
    stahl
    -0.47
    FEA
    -0.47
     ‍
    -0.47
    POSITIVE LOGITS
    k
    0.74
    kk
    0.67
    kkkk
    0.64
    ck
    0.63
    ky
    0.62
    K
    0.61
    ak
    0.60
    𝘬
    0.59
    pk
    0.59
    ke
    0.59
    Activations Density 1.210%

    No Known Activations