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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12642
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kugel
    -0.87
     Creature
    -0.82
     Richelieu
    -0.80
    Municipio
    -0.80
    obium
    -0.79
    afficheront
    -0.78
    ölkerung
    -0.78
     Sardinia
    -0.78
     CDP
    -0.77
     SDGs
    -0.76
    POSITIVE LOGITS
     Past
    2.43
     past
    2.36
    Past
    2.28
    past
    2.19
     PAST
    2.03
    PAST
    1.97
     Vergangenheit
    1.14
     passato
    1.13
     pasada
    1.06
    過去
    1.03
    Activations Density 0.031%

    No Known Activations