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. 15-GEMMASCOPE-RES-16K
    6. 2273
    Prev
    Next
    INDEX
    Explanations

    import statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -1.00
    +#+#
    -0.93
     通販
    -0.77
    ttino
    -0.72
    thâu
    -0.71
    AnchorTagHelper
    -0.69
    brainly
    -0.69
    stateProvider
    -0.69
     '\\;'
    -0.69
    WriteTagHelper
    -0.68
    POSITIVE LOGITS
    import
    0.74
     τί
    0.48
     contigo
    0.47
     Injectable
    0.47
     UIKit
    0.44
     noires
    0.44
     MonoBehaviour
    0.44
     among
    0.44
    FormComponent
    0.43
    ProgressDialog
    0.43
    Activations Density 0.019%

    No Known Activations