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. 505
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to advanced statistical algorithms and modeling

    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
    UnsafeEnabled
    -0.86
     Roskov
    -0.80
     pinulongan
    -0.77
    delwed
    -0.76
     مشين
    -0.75
    Autoritní
    -0.75
    ">//
    -0.73
    rungsseite
    -0.72
    PerformLayout
    -0.71
     Signalez
    -0.70
    POSITIVE LOGITS
    +#+#
    0.49
     fatt
    0.42
    akukan
    0.40
     star
    0.37
    Raises
    0.34
    GMENT
    0.34
     same
    0.34
    STARS
    0.33
    Kirch
    0.33
     stars
    0.33
    Activations Density 1.469%

    No Known Activations