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. 21-GEMMASCOPE-RES-16K
    6. 876
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical models and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.93
    NUMX
    -0.92
     AspNetCore
    -0.87
     незавершена
    -0.87
    +#+#
    -0.86
     utafitiHapana
    -0.84
     متعلقه
    -0.81
     saites
    -0.78
     XNUMX
    -0.78
    findpost
    -0.78
    POSITIVE LOGITS
     $
    1.05
     $\
    0.87
     X
    0.82
     P
    0.76
     R
    0.76
     S
    0.74
     x
    0.73
     ${\
    0.68
     N
    0.67
     M
    0.67
    Activations Density 2.776%

    No Known Activations