© 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. 6187
    Prev
    Next
    INDEX
    Explanations

    references to the term "IR" and related scientific concepts

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

    common prefixes like "IR" and names beginning with "Irfa" or "Ir" in technical or academic contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the prefix "Ir" at the beginning of words.

    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
    enn
    -0.51
    webElement
    -0.47
     Chwiliwch
    -0.45
    AsUp
    -0.45
     فريبيس
    -0.42
    AppMethodBeat
    -0.41
    Been
    -0.40
    aken
    -0.39
    es
    -0.39
     Préférences
    -0.39
    POSITIVE LOGITS
     Ir
    0.56
     ir
    0.54
     irradi
    0.50
    Ir
    0.49
     Chir
    0.49
     irré
    0.47
     Irma
    0.45
     IR
    0.45
    hoeddwyd
    0.45
     irrig
    0.44
    Activations Density 0.418%

    No Known Activations