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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16194
    Prev
    Next
    INDEX
    Explanations

    programming constructs and conditions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SDLK
    -0.56
    föra
    -0.53
     orientale
    -0.51
     '*')
    -0.48
     openings
    -0.47
    خواندن
    -0.47
     shooters
    -0.47
     fiches
    -0.46
     sidan
    -0.46
     '+':
    -0.45
    POSITIVE LOGITS
     Infórmanos
    0.89
    SourceChecksum
    0.77
    StartTag
    0.71
    tagHelper
    0.71
    Tembelea
    0.69
     Савезне
    0.69
    ContentAsync
    0.68
     cherchés
    0.66
    GOTREF
    0.66
    GraphicsUnit
    0.66
    Activations Density 0.002%

    No Known Activations