© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7485
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structures in programming code

    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
    ClCompile
    -0.30
     Cong
    -0.29
     Kong
    -0.28
     œ
    -0.28
    Cong
    -0.28
     Boul
    -0.27
     useSelector
    -0.27
    듬
    -0.26
    WebServlet
    -0.26
     Dur
    -0.26
    POSITIVE LOGITS
     break
    3.20
    break
    3.00
     Break
    2.67
     breaks
    2.59
     BREAK
    2.42
    Break
    2.42
     breaking
    2.39
     Breaks
    2.23
     broke
    2.20
    BREAK
    2.11
    Activations Density 0.222%

    No Known Activations