© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8904
    Prev
    Next
    INDEX
    Explanations

    references to experiments and experimental protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     profilo
    -0.78
     الوطنيه
    -0.70
    OrWhiteSpace
    -0.70
    VOS
    -0.69
    \|_{
    -0.67
    afone
    -0.64
    ########.
    -0.64
    viders
    -0.63
    deserved
    -0.62
     Sass
    -0.61
    POSITIVE LOGITS
     experiment
    3.10
     experiments
    2.97
     Experiment
    2.84
     Experiments
    2.75
    Experiment
    2.66
    experiment
    2.61
     EXPERIMENT
    2.55
    Experiments
    2.48
     experimentation
    2.41
     experimento
    2.33
    Activations Density 0.096%

    No Known Activations