© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4633
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics or circuits

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

    Actions of turning something on/off

    np_acts-logits-general · gemini-2.0-flash

    turned on or off

    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
     '\\;'
    -0.75
    ⓧ
    -0.60
     CURIAM
    -0.60
     Meille
    -0.58
     AspNetCore
    -0.57
    thâu
    -0.56
    bootstrapcdn
    -0.56
    verwijspagina
    -0.55
     propOrder
    -0.54
    MergeFrom
    -0.53
    POSITIVE LOGITS
     turned
    1.17
     Turned
    1.09
     turn
    1.09
    turned
    1.02
    Turn
    1.02
    Turned
    1.02
     Turn
    1.00
     turning
    0.99
     power
    0.98
    turn
    0.97
    Activations Density 0.292%

    No Known Activations