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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 12933
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate the action of pushing or advancing

    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
     portátil
    -0.67
     whiteColor
    -0.66
     telinga
    -0.63
    cein
    -0.62
    rüstung
    -0.59
    aur
    -0.58
    RSpec
    -0.58
     oreilles
    -0.58
    الحياه
    -0.58
     LSA
    -0.58
    POSITIVE LOGITS
     push
    1.78
     PUSH
    1.57
     Push
    1.57
     pushes
    1.56
     Pushing
    1.54
     pushed
    1.49
    push
    1.48
     pushing
    1.46
     pusher
    1.46
    PUSH
    1.45
    Activations Density 0.068%

    No Known Activations