Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 2490
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.97
     surla
    -0.73
    findpost
    -0.72
     '{@
    -0.70
     linkovi
    -0.65
    #+#
    -0.62
    
    -0.62
     Athen
    -0.61
     AssemblyVersion
    -0.58
     بيها
    -0.58
    POSITIVE LOGITS
    pium
    0.59
    fino
    0.58
    ėk
    0.57
    يادة
    0.57
    ();)
    0.55
    tled
    0.54
    élev
    0.54
     بلکه
    0.53
    COLOG
    0.53
    cjon
    0.52
    Activations Density 0.378%

    No Known Activations