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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68141
    Prev
    Next
    INDEX
    Explanations

    references to the IntelliJ programming environment or library

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     trovar
    -0.36
     conosci
    -0.34
    paramMap
    -0.34
     recognised
    -0.33
     gespannt
    -0.33
     diría
    -0.33
     innamor
    -0.32
     erkannt
    -0.32
     boda
    -0.32
     umana
    -0.32
    POSITIVE LOGITS
    intellij
    3.80
    jetbrains
    0.84
     IntelliJ
    0.77
     UnityEditor
    0.72
    netbeans
    0.70
     betweenstory
    0.69
     utafitiHapana
    0.64
    AppMethodBeat
    0.63
     Signalez
    0.60
    vscode
    0.60
    Activations Density 0.001%

    No Known Activations