Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7472
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases associated with scientific analysis and determination

    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
    +#+#
    -1.47
     myſelf
    -1.39
     propOrder
    -1.35
     greateſt
    -1.33
     photolibrary
    -1.33
     itſelf
    -1.32
    StoryboardSegue
    -1.27
     ་་
    -1.26
     purpoſe
    -1.25
     ſever
    -1.23
    POSITIVE LOGITS
     
    1.21
    ,
    1.09
    .
    1.00
     in
    0.96
     a
    0.90
    :
    0.88
     (
    0.88
    (
    0.85
     for
    0.85
    /
    0.83
    Activations Density 0.696%

    No Known Activations