© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3265
    Prev
    Next
    INDEX
    Explanations

    phrases that denote permission or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.74
     perdere
    -0.66
    principalColumn
    -0.66
    TypedDataSet
    -0.64
    UnknownFields
    -0.63
     importar
    -0.61
    igshid
    -0.61
     كومونز
    -0.60
     officielles
    -0.57
     perdió
    -0.56
    POSITIVE LOGITS
     enables
    1.59
     enable
    1.55
     enabling
    1.47
     Enables
    1.40
     allows
    1.37
     enabled
    1.35
     allowing
    1.27
     allow
    1.27
     permet
    1.22
     permits
    1.22
    Activations Density 0.228%

    No Known Activations