© 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. 0-GEMMASCOPE-RES-16K
    11. 7578
    Prev
    Next
    INDEX
    Explanations

    terms indicating permission or facilitation within a process or exploration of features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.64
    amodel
    -0.54
     referenties
    -0.53
    ngdoc
    -0.53
    tellar
    -0.53
     ourselves
    -0.52
    äume
    -0.51
    ativité
    -0.51
     yourself
    -0.51
     myself
    -0.51
    POSITIVE LOGITS
     allowing
    1.87
     Allowing
    1.72
     enabling
    1.63
    allowing
    1.56
     permitting
    1.45
     requiring
    1.44
     permitiendo
    1.27
     forcing
    1.21
     Enabling
    1.20
     encouraging
    1.19
    Activations Density 0.225%

    No Known Activations