© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    references to historical timelines and changes over time

    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
     conducta
    -0.32
     houden
    -0.29
     metodología
    -0.29
     narod
    -0.29
     odkazy
    -0.28
     bakgrund
    -0.28
    setHorizontal
    -0.28
     reciente
    -0.28
     сливо
    -0.28
     obdob
    -0.27
    POSITIVE LOGITS
    early
    1.05
    Early
    1.04
     Early
    0.97
     early
    0.96
     EARLY
    0.91
    EARLY
    0.91
    提前
    0.85
     premature
    0.85
     prematurely
    0.80
    早
    0.80
    Activations Density 0.333%

    No Known Activations