© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7608
    Prev
    Next
    INDEX
    Explanations

    numerical values and variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.65
    $")
    -0.60
     }}$}
    -0.59
    }$​
    -0.59
    */].
    -0.57
    )』
    -0.57
    }")
    
    -0.56
    '},
    
    -0.56
    .*")]
    -0.55
    ')")
    -0.54
    POSITIVE LOGITS
    AddHtmlAttribute
    0.51
    stddef
    0.42
    awtextra
    0.38
    RTSN
    0.38
    GenerationType
    0.36
    treeview
    0.35
     JUDICIAL
    0.34
    วม
    0.33
    permitAll
    0.33
     pesado
    0.33
    Activations Density 1.483%

    No Known Activations