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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 3188
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities involving lesser than or equal to constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.58
     Horv
    -0.58
     diventare
    -0.54
    ergies
    -0.54
    Ỏ
    -0.53
     doccia
    -0.53
     ahli
    -0.52
     bocca
    -0.52
     ifølge
    -0.51
     allerede
    -0.51
    POSITIVE LOGITS
    hoeddwyd
    0.73
    فحة
    0.64
    izzard
    0.61
    djangoproject
    0.61
    Чем
    0.57
    setVerticalGroup
    0.57
    )<\
    0.57
    verwijspagina
    0.56
    cipline
    0.56
     Southgate
    0.56
    Activations Density 0.204%

    No Known Activations