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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13119
    Prev
    Next
    INDEX
    Explanations

    references to challenges and obstacles faced within various contexts

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

    "challenge" and its variations

    np_acts-logits-general · gemini-2.0-flash

    future challenge or challenge Walk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderSide
    -0.62
    
    -0.48
     BoxDecoration
    -0.47
     Bescheid
    -0.45
     Gebrauch
    -0.43
    帖最后由
    -0.39
     yüzde
    -0.39
     vlasy
    -0.37
     verheiratet
    -0.37
     zufolge
    -0.37
    POSITIVE LOGITS
     Challenge
    1.41
    Challenge
    1.34
     CHALLENGE
    1.31
    challenge
    1.30
     Challenges
    1.24
     challenge
    1.24
     Chall
    1.22
     challenges
    1.21
     Challenging
    1.16
    Challenges
    1.14
    Activations Density 0.078%

    No Known Activations