© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6523
    Prev
    Next
    INDEX
    Explanations

    statistics related to population demographics and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     macam
    -0.51
     ulike
    -0.47
    Enllaces
    -0.47
    厚的
    -0.46
     поставить
    -0.44
    えん
    -0.44
    agot
    -0.43
     x
    -0.42
    strix
    -0.42
    主管
    -0.42
    POSITIVE LOGITS
    ]--;
    0.71
     tartalomajánló
    0.70
    adpleegd
    0.69
    ThroughAttribute
    0.69
    StoryboardSegue
    0.67
    ölkerung
    0.65
     Wikimedijinoj
    0.63
    NewUrlParser
    0.62
    WebControls
    0.60
     (>
    0.60
    Activations Density 0.445%

    No Known Activations