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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105148
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax for filtering and sorting elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AddHtmlAttribute
    -0.56
    AndEndTag
    -0.52
     BoxDecoration
    -0.52
    ftagPool
    -0.51
    RegistryLite
    -0.49
     iprot
    -0.46
    XtraEditors
    -0.43
     TextInputType
    -0.43
    cerpt
    -0.42
    ThemeOverlay
    -0.42
    POSITIVE LOGITS
    ########.
    0.43
    mable
    0.39
    Linq
    0.37
    organizzazione
    0.35
     elástica
    0.35
    rachtet
    0.35
    hoebe
    0.34
    godic
    0.34
    DotNetBar
    0.34
    TokenNameRPAREN
    0.34
    Activations Density 0.015%

    No Known Activations