© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7646
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and code structures

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

    Operating system names and system calls

    np_acts-logits-general · gemini-2.0-flash

    importing system APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kepentingan
    -0.36
     مؤرشف
    -0.36
     Finishing
    -0.35
    AddTagHelper
    -0.34
    crud
    -0.34
    Legături
    -0.34
     Gór
    -0.33
     pasaje
    -0.33
    Finishing
    -0.33
     aliqu
    -0.33
    POSITIVE LOGITS
     Windows
    0.64
     windows
    0.63
    getSystemService
    0.61
    DllImport
    0.61
    новништво
    0.58
    Windows
    0.58
     native
    0.57
     WINDOWS
    0.56
     hardware
    0.56
    native
    0.56
    Activations Density 0.813%

    No Known Activations