© 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. 24-GEMMASCOPE-RES-16K
    11. 5357
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of the word 'in' and phrases related to location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    spatial contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.75
     kasarigan
    -0.59
     continúas
    -0.59
     vientre
    -0.55
     الرياضيه
    -0.55
     estekak
    -0.54
    sense
    -0.54
    DriverManager
    -0.54
    estacks
    -0.53
     saites
    -0.53
    POSITIVE LOGITS
     front
    0.81
     silence
    0.59
     shifts
    0.54
     complete
    0.51
    ruptedException
    0.50
    front
    0.50
     broad
    0.49
    //
    0.49
    RectangleBorder
    0.49
    зад
    0.48
    Activations Density 0.220%

    No Known Activations