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. 13-GEMMASCOPE-RES-16K
    6. 4431
    Prev
    Next
    INDEX
    Explanations

    references to improvements or enhancements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edifício
    -0.79
    +#+#
    -0.75
     Bitter
    -0.74
    cyn
    -0.73
     AID
    -0.73
     Aitken
    -0.73
    ..\..\
    -0.70
     Union
    -0.70
    WriteBarrier
    -0.68
     Amin
    -0.67
    POSITIVE LOGITS
     Camila
    1.01
    Camila
    0.86
     chèvre
    0.79
     Cayenne
    0.79
    Romeo
    0.78
     ejus
    0.78
    hancing
    0.78
     Lugo
    0.78
     Epist
    0.78
    esomeness
    0.76
    Activations Density 0.176%

    No Known Activations