© 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. 11-GEMMASCOPE-RES-16K
    6. 4662
    Prev
    Next
    INDEX
    Explanations

    demographic statistics related to population trends and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.58
    -------
    -0.55
    ніципа
    -0.50
    Obrázky
    -0.49
    Vidite
    -0.47
     оригіналу
    -0.47
     Improvements
    -0.46
     iconLine
    -0.44
     defaultstate
    -0.44
    Improvements
    -0.44
    POSITIVE LOGITS
     population
    0.63
     demographic
    0.58
    population
    0.57
     Population
    0.55
     demographics
    0.53
    Population
    0.51
    fastjson
    0.50
     Demographics
    0.47
    Demographics
    0.47
    /***/
    0.45
    Activations Density 0.328%

    No Known Activations