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. 2-GEMMASCOPE-RES-16K
    6. 1110
    Prev
    Next
    INDEX
    Explanations

    verbal actions and programming constructs related to specific programming functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.68
     rencont
    -0.61
     saves
    -0.60
     relaxes
    -0.60
     manages
    -0.60
     sends
    -0.60
     introduces
    -0.59
     forgets
    -0.59
     succeeds
    -0.59
     loses
    -0.59
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    EndInit
    0.64
    ResumeLayout
    0.61
    awt
    0.57
    JButton
    0.56
    ance
    0.56
     cref
    0.53
    ENCE
    0.51
     Inn
    0.50
    ence
    0.49
    Activations Density 1.527%

    No Known Activations