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. 21-GEMMASCOPE-RES-16K
    6. 6907
    Prev
    Next
    INDEX
    Explanations

    terms related to online accessibility and legal regulations regarding information and content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.68
    ValueStyle
    -0.63
    TagHelper
    -0.63
    তথ্যসূত্র
    -0.62
    findpost
    -0.62
     Administrativna
    -0.62
    DotNetBar
    -0.61
    RUnlock
    -0.60
     Paroles
    -0.59
     noqa
    -0.59
    POSITIVE LOGITS
     online
    3.58
    online
    2.96
     Online
    2.85
    Online
    2.79
     ONLINE
    2.64
    ONLINE
    2.43
     internet
    2.31
     Internet
    2.19
     онлайн
    2.17
    Internet
    1.97
    Activations Density 0.455%

    No Known Activations