© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1550
    Prev
    Next
    INDEX
    Explanations

    commands and parameters related to task execution and management within a programming context

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

    Azure CLI commands and related terms

    np_acts-logits-general · gemini-2.0-flash

    acr command names and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bitField
    -0.87
    تقاوى
    -0.86
     transfieras
    -0.85
    protoimpl
    -0.84
    rungsseite
    -0.84
    BeginInit
    -0.82
     Administrativna
    -0.81
     فريبيس
    -0.79
    UnusedPrivate
    -0.79
     المعيارى
    -0.78
    POSITIVE LOGITS
     Area
    0.34
     result
    0.33
     Legacy
    0.32
    langer
    0.32
     Journal
    0.32
     Recovery
    0.32
    userList
    0.32
    口
    0.31
     App
    0.31
    ardin
    0.30
    Activations Density 0.739%

    No Known Activations