© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90844
    Prev
    Next
    INDEX
    Explanations

    references to the Kotlin programming language and its components

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

    kotlin code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.46
     Chwiliwch
    -0.40
    Билгалдахарш
    -0.39
     quedado
    -0.37
    Enllaços
    -0.36
    eqn
    -0.34
     abuelos
    -0.31
     égale
    -0.30
     varones
    -0.30
     lourd
    -0.30
    POSITIVE LOGITS
     Kotlin
    0.72
     kotlin
    0.68
    kotlin
    0.67
    Kotlin
    0.67
    terdam
    0.60
    onesia
    0.59
     outlander
    0.58
     فريبيس
    0.57
    topia
    0.56
     Lana
    0.56
    Activations Density 0.001%

    No Known Activations