© 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. 15-GEMMASCOPE-RES-16K
    11. 5542
    Prev
    Next
    INDEX
    Explanations

    negatives and uncertainties surrounding the state of knowledge or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affari
    -0.47
     Boun
    -0.44
    strecke
    -0.42
     maisha
    -0.41
     noft
    -0.40
     sponge
    -0.40
    princ
    -0.39
     differentials
    -0.39
     Nauk
    -0.39
     cowardly
    -0.39
    POSITIVE LOGITS
    featureID
    0.72
    IVEREF
    0.72
    Билгалдахарш
    0.71
     للمعارف
    0.70
     useAppContext
    0.69
     оригіналу
    0.69
     "..\..\
    0.67
    GHIJKLM
    0.67
    PreExecute
    0.66
     ContentValues
    0.65
    Activations Density 0.304%

    No Known Activations