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. 1621
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical specifications related to conditions or definitions in a formal context

    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
    expandindo
    -0.85
     InputDecoration
    -0.61
     diak
    -0.59
    setVerticalGroup
    -0.56
    سخ
    -0.55
    deu
    -0.55
     Zacks
    -0.54
    ViewInit
    -0.53
     оригіналу
    -0.52
     Información
    -0.52
    POSITIVE LOGITS
     ModelRenderer
    0.66
     urme
    0.65
    UnusedPrivate
    0.64
    KommentareTeilen
    0.64
    Rohy
    0.63
     iconFacebook
    0.62
    complexContent
    0.60
     referrerpolicy
    0.59
    })*/
    0.58
    __);
    0.57
    Activations Density 0.217%

    No Known Activations