© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7031
    Prev
    Next
    INDEX
    Explanations

    references to file operations and layout attributes in code

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

    "file" or file-like objects

    np_acts-logits-general · gemini-2.0-flash

    file, FileInputStream, File

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.62
    AxisAlignment
    -0.61
    ंदीखरीदारी
    -0.58
     newOwner
    -0.54
    ViewFeatures
    -0.54
    TryDecodeAsNil
    -0.49
    enumii
    -0.48
    tangentMode
    -0.46
    tinyos
    -0.46
    IContainer
    -0.45
    POSITIVE LOGITS
     file
    0.66
    UnusedPrivate
    0.49
    <thead>
    0.46
     Roskov
    0.46
    file
    0.42
    FileInputStream
    0.42
     File
    0.41
    baix
    0.39
     frit
    0.39
     FILE
    0.39
    Activations Density 0.115%

    No Known Activations