© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    steps in laboratory protocols related to sample preparation and processing

    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
    gameserver
    -0.50
     spot
    -0.41
     spots
    -0.39
    シロ
    -0.38
     Spot
    -0.38
    RegressionTest
    -0.38
    setVerticalGroup
    -0.36
    tagext
    -0.36
     kasarigan
    -0.35
    goed
    -0.35
    POSITIVE LOGITS
     buffer
    0.93
     buffers
    0.79
    buffer
    0.77
     Buffer
    0.72
    缓冲
    0.68
     buffered
    0.67
    Buffer
    0.66
     BUFFER
    0.63
     buffering
    0.63
     Buff
    0.57
    Activations Density 1.531%

    No Known Activations