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. 0-GEMMASCOPE-RES-16K
    6. 6553
    Prev
    Next
    INDEX
    Explanations

    function calls related to user interface element retrieval in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.67
    arkhand
    -0.62
    mehl
    -0.62
    havior
    -0.60
    ouge
    -0.59
    мания
    -0.57
    fekt
    -0.55
     Folge
    -0.55
    initely
    -0.53
    enumi
    -0.53
    POSITIVE LOGITS
    they
    1.14
    THE
    1.02
    the
    1.01
    there
    0.99
    them
    0.96
    you
    0.92
    he
    0.88
    she
    0.87
    it
    0.84
    his
    0.81
    Activations Density 0.099%

    No Known Activations