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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6080
    Prev
    Next
    INDEX
    Explanations

    coding patterns and structures in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localObject
    -0.30
     me
    -0.26
     tri
    -0.25
     red
    -0.24
     Gerichts
    -0.23
    南浔
    -0.22
     meja
    -0.22
     couple
    -0.22
     dif
    -0.21
    PrototypeOf
    -0.21
    POSITIVE LOGITS
    TypedDataSet
    1.04
    InjectAttribute
    0.99
    Vidite
    0.85
    Autoritní
    0.84
    httphttps
    0.78
     صوتيه
    0.74
    ArrowToggle
    0.74
    RegressionTest
    0.73
    WebVitals
    0.71
    msgTypes
    0.71
    Activations Density 0.401%

    No Known Activations