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. 16-GEMMASCOPE-RES-16K
    6. 12186
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with speed or quickness

    np_acts-logits-general · gemini-2.0-flash

    quick actions and immediacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regolare
    -0.49
    Portály
    -0.49
     prosegu
    -0.46
    KeepAlive
    -0.45
    onuclear
    -0.45
    esterno
    -0.43
    enum
    -0.41
    Lähde
    -0.41
    hibe
    -0.41
    Trama
    -0.40
    POSITIVE LOGITS
     quick
    1.65
     rapid
    1.59
    quick
    1.59
    Rapid
    1.50
     QUICK
    1.49
     quickly
    1.49
     schnell
    1.49
     immedi
    1.45
     Rapid
    1.45
     immediate
    1.44
    Activations Density 0.558%

    No Known Activations