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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8710
    Prev
    Next
    INDEX
    Explanations

    instances of the variable 'i' in programming-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.71
     '\\;'
    -0.68
    styleType
    -0.67
     linkovi
    -0.67
    ьаж
    -0.66
    principalColumn
    -0.65
    PostInfinity
    -0.65
    Cyfarwyddwr
    -0.65
     AssemblyVersion
    -0.65
     otomatig
    -0.63
    POSITIVE LOGITS
    ++)
    0.53
    ++){
    0.34
    eriksaan
    0.32
     ciudadana
    0.30
     promocional
    0.30
     fotográfico
    0.29
     parcs
    0.29
    eamiento
    0.29
    uncios
    0.29
     +=
    0.28
    Activations Density 0.075%

    No Known Activations