© 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. 5-GEMMASCOPE-RES-16K
    11. 6280
    Prev
    Next
    INDEX
    Explanations

    punctuations and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    standig
    -0.61
    팎
    -0.61
    لينا
    -0.60
     Efq
    -0.59
    enapa
    -0.59
     Greeks
    -0.59
     Houſe
    -0.57
    nswer
    -0.57
    requisites
    -0.56
    סף
    -0.56
    POSITIVE LOGITS
    sego
    0.72
     []:
    0.71
    ">—
    0.69
    verwijspagina
    0.68
     /\.(
    0.66
     :
    0.64
    overrightarrow
    0.64
     Numerade
    0.63
    webElement
    0.63
     Audiodateien
    0.62
    Activations Density 0.116%

    No Known Activations