© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8536
    Prev
    Next
    INDEX
    Explanations

    key terms and features related to software applications and programming concepts

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

    relative clauses introduced by "which" that follow nouns or noun phrases.

    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
    MigrationBuilder
    -0.59
    Including
    -0.49
    INCLUDING
    -0.48
     gynnwys
    -0.48
     ویکی‌پدیا
    -0.47
     incluyendo
    -0.47
    toMatchSnapshot
    -0.46
     Including
    -0.44
     incorporating
    -0.44
    __(/*!
    -0.44
    POSITIVE LOGITS
     basically
    0.54
     helps
    0.51
     help
    0.51
     aims
    0.51
    basically
    0.49
    Nationalité
    0.48
     assist
    0.47
    assist
    0.47
     essentially
    0.46
     lets
    0.46
    Activations Density 0.777%

    No Known Activations