© 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. 377
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their descriptions

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

    articles describing organizations, non-profits, and institutions with their official names and purposes.

    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
     يتيمه
    -0.61
     chamada
    -0.45
    RegressionTest
    -0.43
     ProtoMessage
    -0.43
     estekak
    -0.42
     correspondiente
    -0.42
    owohl
    -0.41
    Either
    -0.41
     Kategorien
    -0.40
    adpleegd
    -0.40
    POSITIVE LOGITS
     collaborative
    0.77
     multi
    0.76
     initiative
    0.73
     multipurpose
    0.67
     multimedia
    0.65
     multifunctional
    0.61
     interactive
    0.59
     grassroots
    0.59
     colloquial
    0.59
     multicultural
    0.59
    Activations Density 0.604%

    No Known Activations