© 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. 3-GEMMASCOPE-RES-16K
    6. 9244
    Prev
    Next
    INDEX
    Explanations

    calls to action or prompts for reader engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.59
    ⓧ
    -0.38
     tatuajes
    -0.36
    /**
    -0.36
     חיצוניים
    -0.35
     azar
    -0.34
     ladrillo
    -0.34
    ásra
    -0.34
     cejas
    -0.34
     residencial
    -0.34
    POSITIVE LOGITS
    <bos>
    0.52
     initComponents
    0.49
     conserv
    0.48
     Cor
    0.47
    icordia
    0.45
    evos
    0.44
    ritation
    0.44
    RTDA
    0.44
    RefNanny
    0.44
     Vamos
    0.43
    Activations Density 0.171%

    No Known Activations