© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8992
    Prev
    Next
    INDEX
    Explanations

    structured formats and metadata tags used in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.05
     ―――――
    -0.94
     myſelf
    -0.85
    تقاوى
    -0.85
     iſt
    -0.85
     himſelf
    -0.84
     المعرف
    -0.84
    AsUp
    -0.83
     Anſ
    -0.81
    +#+
    -0.80
    POSITIVE LOGITS
    gemäß
    0.67
     Duncan
    0.61
    $_['
    0.61
    ↵↵
    0.60
    しくは
    0.60
    "]=
    0.59
     the
    0.59
     The
    0.57
    );?>
    0.56
    ivar
    0.56
    Activations Density 0.385%

    No Known Activations