© 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. 9-GEMMASCOPE-RES-16K
    6. 11407
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hijas
    -0.42
     will
    -0.41
     mão
    -0.39
     is
    -0.39
     Investigaciones
    -0.37
     salvajes
    -0.37
     esté
    -0.36
     rayas
    -0.35
     propuesto
    -0.35
     Boden
    -0.35
    POSITIVE LOGITS
     ―――――
    0.78
     ſind
    0.78
     verſ
    0.77
    batore
    0.76
     ſei
    0.75
    ſammen
    0.73
    __(/*!
    0.70
    iſter
    0.70
    iſen
    0.69
     Monfieur
    0.69
    Activations Density 0.270%

    No Known Activations