© 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. 3-GEMMASCOPE-RES-16K
    11. 5786
    Prev
    Next
    INDEX
    Explanations

    strings indicative of markup or HTML tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     efforts
    -0.49
     majority
    -0.46
    
    -0.44
     nor
    -0.44
     Perry
    -0.43
     Nor
    -0.42
     fact
    -0.42
     ado
    -0.42
    rony
    -0.42
     ‍
    -0.42
    POSITIVE LOGITS
     "<
    2.14
     '<
    2.06
    ("<
    2.02
    ('<
    1.86
    '<
    1.85
    "<
    1.84
    ="<
    1.57
     `<
    1.41
    `<
    1.38
     $("<
    1.21
    Activations Density 0.107%

    No Known Activations