© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7603
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical expressions, particularly involving variables and functions

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

    hexadecimal numbers and numeric codes in technical or scientific documents.

    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
     Secondly
    -0.68
    httphttps
    -0.63
    Secondly
    -0.63
    asteroido
    -0.62
    Secondary
    -0.58
     secondly
    -0.55
     &___
    -0.54
    IndentedString
    -0.54
     secundarios
    -0.54
     Secondary
    -0.53
    POSITIVE LOGITS
     Mark
    0.41
     desar
    0.40
     Act
    0.38
    CppMethod
    0.37
    asp
    0.35
    tvguidetime
    0.35
    ض
    0.34
     Gl
    0.34
     Feldman
    0.34
     الدر
    0.33
    Activations Density 1.650%

    No Known Activations