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. 11-GEMMASCOPE-RES-16K
    6. 10091
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearances, particularly related to hair and eye color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.47
    RuleContext
    -0.46
    ClientRect
    -0.40
    UnsafeEnabled
    -0.40
    addContainerGap
    -0.40
    cshtml
    -0.39
     passagem
    -0.39
    off
    -0.37
     verzorg
    -0.37
     Crisp
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.80
    PerformLayout
    0.45
     propOrder
    0.44
     skippy
    0.42
     ſy
    0.42
    RTEX
    0.41
    ArgsConstructor
    0.40
     FontFamily
    0.39
    thâu
    0.39
    autoIncrement
    0.39
    Activations Density 0.372%

    No Known Activations