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. 12-GEMMASCOPE-RES-16K
    6. 1330
    Prev
    Next
    INDEX
    Explanations

    technical jargon and complex terms associated with software or hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.00
    ymce
    -0.86
    principalTable
    -0.85
    erializer
    -0.84
    IPAC
    -0.84
    >{@
    -0.83
    PerformLayout
    -0.80
     ✭✭
    -0.76
    mobileqq
    -0.76
    曖昧さ回避
    -0.76
    POSITIVE LOGITS
     itſelf
    1.09
     myſelf
    1.09
     Jefus
    1.09
     Majefty
    1.08
     whoſe
    1.08
     ſtate
    1.08
     himſelf
    1.03
     themſelves
    1.01
     becauſe
    1.01
     Reſ
    1.00
    Activations Density 2.583%

    No Known Activations