Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 3156
    Prev
    Next
    INDEX
    Explanations

    intensifiers and modifiers that amplify descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gameserver
    -0.73
     adaptées
    -0.60
     escuchadas
    -0.59
     tjen
    -0.56
    PerformLayout
    -0.56
     Sorgen
    -0.56
    inhos
    -0.56
    nehin
    -0.56
    isNotBlank
    -0.55
     respectivos
    -0.54
    POSITIVE LOGITS
     ULTRA
    0.78
     insanely
    0.75
     incredibly
    0.72
     ultra
    0.71
     extreme
    0.71
     absolute
    0.70
     ridiculously
    0.69
     ultras
    0.67
     unbelievably
    0.66
     extremely
    0.66
    Activations Density 0.178%

    No Known Activations