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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 114541
    Prev
    Next
    INDEX
    Explanations

    code snippets related to user interface interactions and scroll functionality

    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
     виправивши
    -0.64
    enderror
    -0.60
    httphttps
    -0.57
    TResult
    -0.57
     Infórmanos
    -0.56
     mCurrent
    -0.55
    脚注の使い方
    -0.55
     يتيمه
    -0.55
     dieſer
    -0.54
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
     suivante
    0.34
     judiciales
    0.34
     contigo
    0.33
    MethodManager
    0.31
     suele
    0.31
     eléctrico
    0.29
     محفوظة
    0.29
     obicei
    0.29
     attention
    0.28
     Dostupné
    0.28
    Activations Density 0.047%

    No Known Activations