© 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. 15-GEMMASCOPE-RES-16K
    6. 8122
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to various fields such as medicine and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -1.25
    r
    -1.15
    k
    -1.14
    t
    -1.12
    l
    -1.10
    m
    -1.07
    ng
    -0.99
    p
    -0.98
    d
    -0.94
    s
    -0.93
    POSITIVE LOGITS
    annica
    1.14
    tvguidetime
    1.07
    elfare
    1.06
     raiſ
    1.05
     Forumite
    1.04
     Bolshe
    1.03
     poffe
    1.03
     LDA
    1.02
    polation
    1.02
    wiſe
    1.02
    Activations Density 0.873%

    No Known Activations