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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to class definitions and method 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$​
    -0.53
    
    -0.52
     ModelRenderer
    -0.50
    toContain
    -0.49
    getColumnIndex
    -0.49
    classnames
    -0.48
    newArrayList
    -0.47
    ARROLL
    -0.47
    oblo
    -0.47
     Forsch
    -0.46
    POSITIVE LOGITS
    HostException
    0.65
    complexContent
    0.54
     AssemblyCulture
    0.53
    AxisAlignment
    0.48
    AddTagHelper
    0.46
    AndroidJUnit
    0.45
    RegistryLite
    0.43
     nakalista
    0.42
    Sklici
    0.41
    ContentAsync
    0.39
    Activations Density 0.134%

    No Known Activations