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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3301
    Prev
    Next
    INDEX
    Explanations

    Java method calls involving "set" and "get" operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    DockStyle
    -0.44
    tagHelperRunner
    -0.39
    altri
    -0.34
    should
    -0.33
    indeed
    -0.32
    AlertDialog
    -0.32
     canst
    -0.32
    such
    -0.32
    centralwidget
    -0.31
    ServletContext
    -0.31
    POSITIVE LOGITS
    MessageOf
    0.67
    IndentedString
    0.64
     useStyles
    0.58
    Portale
    0.56
    libft
    0.54
     primary
    0.53
     disponibilités
    0.53
     handlebar
    0.52
    <bos>
    0.52
    prüche
    0.52
    Activations Density 0.056%

    No Known Activations