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. 5-GEMMASCOPE-RES-16K
    6. 9857
    Prev
    Next
    INDEX
    Explanations

    file path references in programming or markup context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.88
    InputBorder
    -0.84
     propOrder
    -0.83
    CloseOperation
    -0.83
    Hozzáférés
    -0.82
    jsonwebtoken
    -0.76
     demur
    -0.76
    SharedDtor
    -0.74
    ագրություններ
    -0.73
    aarrggbb
    -0.70
    POSITIVE LOGITS
     '../
    2.75
     "../
    2.58
    ('../
    2.21
    ("../
    2.05
     './../
    1.90
     '../../
    1.85
     "../../
    1.81
     '../../../
    1.61
    "../
    1.56
     ../
    1.54
    Activations Density 0.015%

    No Known Activations