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. 20-GEMMASCOPE-RES-16K
    6. 1961
    Prev
    Next
    INDEX
    Explanations

    code elements and configurations related to JavaScript and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.54
    حوالہ
    -0.53
     صوتيه
    -0.51
    越大
    -0.50
    argas
    -0.48
     OGSÅ
    -0.47
    ãy
    -0.47
     ComVisible
    -0.47
     Untold
    -0.47
     genomen
    -0.47
    POSITIVE LOGITS
    AutoScaleMode
    0.59
    dist
    0.54
     index
    0.53
    src
    0.52
    index
    0.51
    endants
    0.49
    uerre
    0.49
     Roskov
    0.49
    FormTagHelper
    0.49
    WriteBarrier
    0.48
    Activations Density 0.138%

    No Known Activations