© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5728
    Prev
    Next
    INDEX
    Explanations

    Keywords related to classification and reference marking, particularly in formal or technical contexts

    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
     EconPapers
    -0.83
    хьтан
    -0.68
     fermés
    -0.66
    сылкі
    -0.65
    neté
    -0.65
     disambiguazione
    -0.65
     nahilalakip
    -0.64
    WithIOException
    -0.63
     régulière
    -0.63
    neries
    -0.63
    POSITIVE LOGITS
     via
    0.61
     online
    0.57
    via
    0.52
     Via
    0.49
    Via
    0.49
     en
    0.47
     through
    0.46
    Batis
    0.46
     on
    0.46
     para
    0.45
    Activations Density 0.585%

    No Known Activations