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. 13-GEMMASCOPE-RES-16K
    6. 5296
    Prev
    Next
    INDEX
    Explanations

    terms related to authentication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LoginComponent
    -0.82
     nahilalakip
    -0.73
    sistors
    -0.72
    RenderAtEndOf
    -0.71
     creeks
    -0.71
    プリング
    -0.70
    LEEP
    -0.69
    coroutines
    -0.69
    ✨:
    -0.69
    peen
    -0.69
    POSITIVE LOGITS
     Auth
    1.24
     auth
    1.08
    AUTH
    1.08
     AUTH
    1.02
    Auth
    1.02
    auth
    1.01
    isAuth
    1.00
     Auer
    0.93
     colgantes
    0.85
    Aud
    0.85
    Activations Density 0.094%

    No Known Activations