© 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. 15-GEMMASCOPE-RES-16K
    11. 4660
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures related to package management and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tslint
    -0.79
     tartalomajánló
    -0.77
     contextLoads
    -0.74
    +#+
    -0.74
    UFACT
    -0.72
    पया
    -0.71
    Xna
    -0.70
    geving
    -0.69
    praš
    -0.68
    appspot
    -0.67
    POSITIVE LOGITS
    <eos>
    0.87
    ↵↵
    0.72
    </code>
    0.58
    ↵
    0.56
    ():
    0.53
    ():
    0.51
    ()->
    0.49
    }}_
    0.49
    сен
    0.48
    ":
    0.47
    Activations Density 0.279%

    No Known Activations