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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 9730
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "function" and its associated test cases in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.28
     Diſ
    -1.02
    ſelf
    -1.01
     poffible
    -1.00
     ſeveral
    -1.00
     Jefus
    -0.99
     raiſ
    -0.97
     myſelf
    -0.97
     whoſe
    -0.97
     Majefty
    -0.96
    POSITIVE LOGITS
     ActionResult
    0.92
     IActionResult
    0.69
    ?
    0.64
    ptus
    0.62
    synthesize
    0.62
     LeBlanc
    0.60
     exp
    0.60
     start
    0.59
     import
    0.59
     abgerufen
    0.58
    Activations Density 0.024%

    No Known Activations