© 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. 38-GEMMASCOPE-RES-16K
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    specific contributions and acknowledgments in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gând
    -0.26
     geplaatst
    -0.26
     început
    -0.25
    mẫu
    -0.24
     regular
    -0.24
     semn
    -0.24
     toege
    -0.24
     ameste
    -0.24
     depend
    -0.24
     voort
    -0.24
    POSITIVE LOGITS
     Zhang
    1.30
     Wang
    1.23
     Liu
    1.18
    Zhang
    1.15
     Chen
    1.13
     Zhou
    1.12
    Wang
    1.10
     Li
    1.07
     Zhao
    1.05
    Liu
    1.05
    Activations Density 0.458%

    No Known Activations