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. 12-GEMMASCOPE-RES-16K
    6. 15244
    Prev
    Next
    INDEX
    Explanations

    identifiers and terms related to governmental and scientific projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništ
    -0.46
    poel
    -0.40
    erráneo
    -0.38
     Never
    -0.38
    oo
    -0.38
     τους
    -0.36
    Never
    -0.36
     Réalisation
    -0.35
    ViewGroup
    -0.35
     relevant
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    1.15
    tvguidetime
    0.84
    出版年
    0.81
    lapsingToolbar
    0.81
    complexContent
    0.76
    তথ্যসূত্র
    0.71
    Kjelder
    0.70
    IUrlHelper
    0.68
    EXTERN
    0.68
     vété
    0.66
    Activations Density 0.844%

    No Known Activations