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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 7533
    Prev
    Next
    INDEX
    Explanations

    numerical data and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.54
    花板
    -0.51
    utnik
    -0.51
    entieth
    -0.48
     sixteen
    -0.47
     Sixteen
    -0.46
     useStyles
    -0.46
     Fourteen
    -0.45
     onCancelled
    -0.44
    Clik
    -0.43
    POSITIVE LOGITS
     third
    1.86
     Third
    1.78
     ketiga
    1.75
    3
    1.71
    third
    1.70
     three
    1.68
    Third
    1.64
     trio
    1.64
     thirds
    1.59
     Three
    1.57
    Activations Density 1.825%

    No Known Activations