© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 378
    Prev
    Next
    INDEX
    Explanations

    references to significant individual performances in sports

    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
    Unlock
    -0.44
     DataLoader
    -0.40
    curacies
    -0.39
     Unlock
    -0.38
     Unions
    -0.38
    AutoresizingMask
    -0.38
     StringTokenizer
    -0.38
    glises
    -0.37
    WriteBarrier
    -0.37
     marcha
    -0.36
    POSITIVE LOGITS
     blocking
    0.70
     intercept
    0.69
     blocks
    0.66
     interception
    0.65
     intercepts
    0.63
     blocked
    0.59
     Intercept
    0.58
     block
    0.56
     intercepted
    0.56
     interference
    0.54
    Activations Density 0.122%

    No Known Activations