© 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. 23-GEMMASCOPE-RES-16K
    11. 14317
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and capabilities in terms of effort and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demikian
    -0.54
    ">—
    -0.53
     truer
    -0.49
     indeed
    -0.49
     quoque
    -0.48
     disambiguazione
    -0.47
     semula
    -0.45
     sàng
    -0.44
     például
    -0.44
     genauer
    -0.43
    POSITIVE LOGITS
     possibly
    1.18
    possibly
    1.12
     Possibly
    1.10
     possible
    1.04
     POSS
    1.03
    possible
    0.96
     Possible
    0.96
    Possibly
    0.95
     POSSIBLE
    0.94
    Possible
    0.90
    Activations Density 0.134%

    No Known Activations