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. 12370
    Prev
    Next
    INDEX
    Explanations

    error messages and return statements in code snippets

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

    Code snippets or program code

    np_acts-logits-general · gemini-2.0-flash

    HBV RNA

    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
    ANTLR
    -0.59
    ipedi
    -0.48
    Extinguishing
    -0.45
    Hoo
    -0.45
    spl
    -0.44
    TimeSpan
    -0.43
     brag
    -0.43
    ziplin
    -0.42
    beu
    -0.41
    äsent
    -0.41
    POSITIVE LOGITS
     Monfieur
    1.02
     purpoſe
    1.01
     myſelf
    0.95
     himſelf
    0.92
     themſelves
    0.88
     Diſ
    0.87
     ſeveral
    0.86
     itſelf
    0.85
     whoſe
    0.84
     ſever
    0.84
    Activations Density 0.063%

    No Known Activations