© 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. 33-GEMMASCOPE-RES-16K
    11. 8249
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and parameters used in statistical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.76
    rungsseite
    -0.58
    AnchorStyles
    -0.55
    MLLoader
    -0.54
     ***!
    -0.53
     مرئيه
    -0.52
    ]")]
    -0.50
    Viitteet
    -0.49
    EndProject
    -0.47
    AutoresizingMask
    -0.47
    POSITIVE LOGITS
     n
    1.55
     N
    1.29
    N
    0.96
    n
    0.95
    ｎ
    0.75
    𝑛
    0.74
    getN
    0.73
     nth
    0.68
    setN
    0.67
     m
    0.63
    Activations Density 2.641%

    No Known Activations