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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9807
    Prev
    Next
    INDEX
    Explanations

    file-related data and variables within code or technical contexts

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

    File names, types, and paths

    np_acts-logits-general · gemini-2.0-flash

    file and directory operations in code

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Formación
    -0.42
     Gestão
    -0.37
     journaux
    -0.35
    providedIn
    -0.35
     BorderSide
    -0.35
     comigo
    -0.34
     formação
    -0.33
     MainAxisSize
    -0.33
     formación
    -0.33
    WithMany
    -0.33
    POSITIVE LOGITS
    VIAF
    0.58
     Roskov
    0.57
    nloa
    0.57
    IUrlHelper
    0.56
    msgTypes
    0.54
    тьяна
    0.52
    Autoritní
    0.49
     FileInputStream
    0.48
     gabbana
    0.48
    URLException
    0.48
    Activations Density 0.049%

    No Known Activations