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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 80028
    Prev
    Next
    INDEX
    Explanations

    variable and function declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    function calls and structure definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    WritableDatabase
    -0.36
    ParallelGroup
    -0.34
    stdc
    -0.34
    มาะ
    -0.34
     اتحاد
    -0.34
     descobri
    -0.32
     vlast
    -0.32
    viewDidLoad
    -0.32
    깐
    -0.32
     comprehensively
    -0.31
    POSITIVE LOGITS
     незавершена
    0.65
    Expedia
    0.61
    хьтан
    0.53
    errHandler
    0.52
    contentLoaded
    0.52
    richTextPanel
    0.51
    UrlResolution
    0.48
    发表于
    0.48
     transfieras
    0.47
    AddTagHelper
    0.47
    Activations Density 0.028%

    No Known Activations