© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8346
    Prev
    Next
    INDEX
    Explanations

    concepts related to underdog scenarios and numerical disadvantage

    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
     igény
    -0.49
     PLWABN
    -0.48
    enido
    -0.48
    tyfik
    -0.48
    cardinal
    -0.48
     مشين
    -0.47
     sosp
    -0.47
    UrlResolution
    -0.46
    ptest
    -0.46
    klaus
    -0.46
    POSITIVE LOGITS
     outnumbered
    0.99
     powerless
    0.75
     defeat
    0.72
     unarmed
    0.68
     overpowered
    0.65
     overwhelm
    0.64
     defeats
    0.64
     defeated
    0.62
     overpowering
    0.62
     overwhel
    0.62
    Activations Density 0.252%

    No Known Activations