© 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. 10-GEMMASCOPE-RES-16K
    11. 12856
    Prev
    Next
    INDEX
    Explanations

    references to sources and citations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.72
    MemoryWarning
    -0.70
    expandindo
    -0.67
    PreferredItem
    -0.66
    __':
    -0.57
    %"),
    -0.57
    Chham
    -0.57
     $_[
    -0.56
    addGap
    -0.55
     Himo
    -0.55
    POSITIVE LOGITS
    source
    2.17
     source
    1.77
    Source
    1.56
     Source
    1.44
     SOURCE
    1.33
    SOURCE
    1.30
    ource
    1.16
    sources
    1.13
     sources
    1.12
    getSource
    1.09
    Activations Density 0.066%

    No Known Activations