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. 3-GEMMASCOPE-RES-16K
    6. 8304
    Prev
    Next
    INDEX
    Explanations

    instances of the word "above" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ril
    -0.58
    er
    -0.55
    cal
    -0.54
    ed
    -0.54
    ClickListener
    -0.53
    []){
    -0.53
    😭😭
    -0.52
    ll
    -0.52
    riwal
    -0.52
     cal
    -0.51
    POSITIVE LOGITS
     above
    2.99
     Above
    2.91
    Above
    2.90
    above
    2.84
     ABOVE
    2.82
    ABOVE
    2.37
    bove
    2.26
     acima
    2.14
     boven
    1.85
     sopra
    1.84
    Activations Density 0.061%

    No Known Activations