© 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. 4-GEMMASCOPE-RES-16K
    11. 11633
    Prev
    Next
    INDEX
    Explanations

    semantic markers related to connectivity and relationships between different elements within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.77
     namelijk
    -0.59
     affich
    -0.47
     langt
    -0.46
     nemlig
    -0.45
     nämlich
    -0.42
    7
    -0.42
    Pipes
    -0.42
     coupable
    -0.41
     pfe
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.73
    Personensuche
    0.72
    حوالہ
    0.72
    itinéraire
    0.69
     Савезне
    0.69
     ويكيميديا
    0.67
    Vidite
    0.67
    //
    0.66
    MigrationBuilder
    0.66
    namon
    0.66
    Activations Density 1.266%

    No Known Activations