© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9260
    Prev
    Next
    INDEX
    Explanations

    elements related to technical or scientific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.63
    MemoryWarning
    -0.58
     يتيمه
    -0.54
     IBOutlet
    -0.53
    .³
    -0.48
    ArgsConstructor
    -0.45
    참고
    -0.45
    Kaieteur
    -0.44
    .¹
    -0.43
    IBOutlet
    -0.42
    POSITIVE LOGITS
     miniaturka
    0.58
     mijne
    0.54
     zijne
    0.49
     antidesliz
    0.47
    odils
    0.46
     kapture
    0.45
     zwey
    0.45
     sodio
    0.44
    tispiece
    0.44
     desmotivaciones
    0.43
    Activations Density 1.272%

    No Known Activations