© 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. 31-GEMMASCOPE-RES-16K
    11. 3443
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and parameters

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

    numerical values and quantities, particularly those presented with units or in specific measurement formats.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.58
     ""],
    -0.52
    enumi
    -0.52
    AnimationsModule
    -0.47
    PerformLayout
    -0.43
    ParallelGroup
    -0.41
    MathML
    -0.41
     ویکی‌آمباردا
    -0.41
    AutoScale
    -0.40
    ger
    -0.39
    POSITIVE LOGITS
     Waſſer
    0.68
    <unused16>
    0.68
    <unused74>
    0.67
    <unused14>
    0.67
    <unused17>
    0.67
    <unused8>
    0.67
    <unused43>
    0.67
    <unused52>
    0.67
    <unused51>
    0.67
    <unused3>
    0.66
    Activations Density 2.330%

    No Known Activations