© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104581
    Prev
    Next
    INDEX
    Explanations

    elements related to job listing attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    EndContext
    -0.48
    lwjgl
    -0.46
    DeleteBehavior
    -0.43
    ContentLoaded
    -0.40
    httphttps
    -0.37
     ujednoznacz
    -0.36
    usepackage
    -0.35
    iforms
    -0.35
    ง
    -0.34
     kaarangay
    -0.33
    POSITIVE LOGITS
    yntaxException
    0.50
     AssemblyCompany
    0.49
     purpoſe
    0.47
     ſtate
    0.46
     AssemblyCulture
    0.46
    đầm
    0.44
    PerformLayout
    0.44
    tvguidetime
    0.44
     myſelf
    0.42
     Majefty
    0.42
    Activations Density 0.012%

    No Known Activations