© 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. 16-GEMMASCOPE-RES-16K
    6. 13334
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability or capacity constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reducido
    -0.43
     Herstellung
    -0.41
     assic
    -0.40
     duração
    -0.40
     asegurar
    -0.40
     dauert
    -0.39
     entendido
    -0.39
     pouvoirs
    -0.38
     négo
    -0.37
     essais
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.59
     exhausted
    0.57
     kasarigan
    0.56
     nahilalakip
    0.54
     maxed
    0.53
    ViewFeatures
    0.52
    таратура
    0.50
    ToBounds
    0.48
    liebte
    0.47
    исленность
    0.46
    Activations Density 0.207%

    No Known Activations