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. 12282
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts regarding purpose or intention

    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
    ൊ
    -0.46
     στιγ
    -0.45
    räck
    -0.44
    jois
    -0.44
     achet
    -0.43
     OPEC
    -0.42
     bety
    -0.42
    Vr
    -0.41
     fatos
    -0.41
     Euphrates
    -0.40
    POSITIVE LOGITS
    ]--;
    0.99
     myſelf
    0.84
    )";
    
    0.81
    RectangleBorder
    0.77
    NUMX
    0.77
     Baillar
    0.75
     internetowa
    0.74
    بوابة
    0.73
    AccessorTable
    0.72
    ]";
    0.72
    Activations Density 0.374%

    No Known Activations