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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 7731
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "Friday" along with references to the winter season

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.63
    reach
    -0.61
     Circum
    -0.59
    REACH
    -0.58
    Reach
    -0.58
     betyr
    -0.58
     commonest
    -0.57
     circon
    -0.57
     adjournment
    -0.57
     känd
    -0.56
    POSITIVE LOGITS
    ReusableCell
    0.78
    mybatisplus
    0.77
     gynhyrchwyd
    0.67
    giène
    0.64
     للمعارف
    0.60
    zsche
    0.60
    ModelSerializer
    0.60
    opathie
    0.59
     Bourgoin
    0.59
    InputModule
    0.58
    Activations Density 0.125%

    No Known Activations