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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12606
    Prev
    Next
    INDEX
    Explanations

    references to children and their needs and experiences

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

    Refers to people using pronouns

    np_acts-logits-general · gemini-2.0-flash

    referring to them and their people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simplifié
    -0.48
    oredCriteria
    -0.40
    toPromise
    -0.40
    smithy
    -0.39
    SBATCH
    -0.38
    はじめに
    -0.38
     Zink
    -0.37
    parsedMessage
    -0.36
    آیا
    -0.35
    mander
    -0.35
    POSITIVE LOGITS
    Their
    0.61
     they
    0.60
    彼らは
    0.60
     Their
    0.59
     họ
    0.56
     their
    0.55
    他們的
    0.55
    他们的
    0.54
    เขา
    0.54
    They
    0.53
    Activations Density 0.411%

    No Known Activations