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. 12799
    Prev
    Next
    INDEX
    Explanations

    instances of software-related issues or errors

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

    a technical problem or issue

    np_acts-logits-general · gemini-2.0-flash

    describing problems or issues

    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
    Gambas
    -0.71
    webElementXpaths
    -0.64
     AssemblyProduct
    -0.62
     Bourgoin
    -0.59
    ttino
    -0.59
     صوتيه
    -0.59
    BeginContext
    -0.58
    textTheme
    -0.58
    istle
    -0.57
    luor
    -0.56
    POSITIVE LOGITS
     symptom
    0.82
     intermittent
    0.80
     intermittently
    0.79
     erratic
    0.78
     problem
    0.75
     issue
    0.73
     mysteriously
    0.72
     symptoms
    0.72
     problema
    0.70
    mittent
    0.69
    Activations Density 0.371%

    No Known Activations