© 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. 14362
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "inter" or interactions in various contexts

    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
    chtigkeit
    -0.71
     bygga
    -0.68
    toJson
    -0.67
    zahlt
    -0.66
    ̀n
    -0.65
    CGSize
    -0.65
    <?>>
    -0.63
     Smarty
    -0.61
    ❯
    -0.61
     Beyer
    -0.60
    POSITIVE LOGITS
     INTER
    1.42
     inter
    1.37
     Inter
    1.31
    INTER
    1.30
    Inter
    1.28
     Inters
    1.22
    Inters
    1.13
    inter
    1.13
     interp
    1.10
     interns
    1.05
    Activations Density 0.109%

    No Known Activations