© 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. 35-GEMMASCOPE-RES-16K
    6. 14822
    Prev
    Next
    INDEX
    Explanations

    criteria for selecting studies in a meta-analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.38
     NUKAT
    -0.32
    tinyos
    -0.30
     disfru
    -0.29
     AppColors
    -0.29
    ガン
    -0.28
    Effect
    -0.28
     oport
    -0.27
    bootstrapcdn
    -0.27
    !*\
    -0.27
    POSITIVE LOGITS
     criteria
    2.98
     Criteria
    2.56
     criterion
    2.45
    criteria
    2.42
     CRITERIA
    2.39
    Criteria
    2.36
     critères
    2.25
     Kriterien
    2.20
     criter
    2.16
     criterios
    2.06
    Activations Density 1.211%

    No Known Activations