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. 12196
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logic structures in programming code

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

    pre-existence or a prior state

    np_acts-logits-general · gemini-2.0-flash

    if it already exists

    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
    __':
    -0.66
     Савезне
    -0.61
    MLLoader
    -0.57
    __":
    -0.56
    abestanden
    -0.50
     שוליים
    -0.50
    __':
    
    -0.50
     OFDb
    -0.49
    âche
    -0.49
    OGND
    -0.49
    POSITIVE LOGITS
     already
    1.43
     existing
    1.29
    already
    1.26
     Existing
    1.21
    existing
    1.19
     Already
    1.19
    Existing
    1.12
     preexisting
    1.11
     EXISTING
    1.10
     previously
    1.08
    Activations Density 0.202%

    No Known Activations