© 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. 7046
    Prev
    Next
    INDEX
    Explanations

    elements associated with technology and data systems

    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
     joão
    -0.43
    Brainz
    -0.42
    AddAttribute
    -0.40
    /******/
    -0.40
     विश्वसनीयता
    -0.40
     HomeController
    -0.39
     purpoſe
    -0.39
    afficheront
    -0.39
    Eloquent
    -0.38
    瘍
    -0.38
    POSITIVE LOGITS
     based
    2.34
    based
    2.17
     Based
    2.06
     BASED
    2.03
    Based
    2.03
    BASED
    1.90
     driven
    1.69
     basado
    1.54
     basada
    1.49
     oriented
    1.48
    Activations Density 1.621%

    No Known Activations