© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    references to mental and physical impairments, and concepts related to sustainability and environmental practices

    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
    NOPQRST
    -0.70
    gameserver
    -0.63
     négociations
    -0.61
    PullParser
    -0.59
    UnusedPrivate
    -0.57
     acoper
    -0.55
     Taktlose
    -0.54
    nagem
    -0.53
     cadrul
    -0.53
     guapos
    -0.53
    POSITIVE LOGITS
    stdc
    0.69
     oprot
    0.66
     برانيه
    0.56
    WebVitals
    0.56
     оригіналу
    0.56
    DateTimeField
    0.53
    bram
    0.50
     gens
    0.50
     blocks
    0.49
    migrationBuilder
    0.49
    Activations Density 0.816%

    No Known Activations