© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and functionalities of systems or software

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

    words and phrases describing separate or distinct components, processes, or entities.

    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
    mtrl
    -0.44
    érat
    -0.39
    BASEPATH
    -0.39
    endphp
    -0.39
     keluarganya
    -0.38
    esgue
    -0.37
     rodeado
    -0.36
     ää
    -0.36
     Pasal
    -0.35
    újo
    -0.35
    POSITIVE LOGITS
     separate
    3.28
    separate
    3.03
     Separate
    2.97
    Separate
    2.94
     seperate
    2.81
     separately
    2.77
     SEPAR
    2.61
     terpisah
    2.45
     separado
    2.33
    Separ
    2.31
    Activations Density 1.886%

    No Known Activations