© 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. 36-GEMMASCOPE-RES-16K
    6. 7558
    Prev
    Next
    INDEX
    Explanations

    references to specific items or elements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.54
    SequentialGroup
    -0.52
     kasarigan
    -0.42
     оригіналу
    -0.41
    रीदारी
    -0.40
     nonUne
    -0.39
     CanadaChoose
    -0.39
    ądze
    -0.39
    AsUp
    -0.38
     esternos
    -0.38
    POSITIVE LOGITS
     few
    3.25
    few
    2.73
    Few
    2.59
     Few
    2.44
     quelques
    2.27
     FEW
    2.14
     birkaç
    2.02
     paar
    1.98
     wenigen
    1.95
     wenige
    1.90
    Activations Density 0.975%

    No Known Activations