© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5795
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

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

    Mathematical variables and expressions

    np_acts-logits-general · gemini-2.0-flash

    numerical comparisons and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sapato
    -0.64
    pulseira
    -0.63
     للمعارف
    -0.63
    tagHelperRunner
    -0.57
    URLException
    -0.57
    RetentionPolicy
    -0.56
     pensamentos
    -0.55
    cartão
    -0.55
     Exactos
    -0.53
    BagConstraints
    -0.53
    POSITIVE LOGITS
    XmlAccessType
    0.35
    sistor
    0.30
    makeConstraints
    0.30
    temuan
    0.29
    quité
    0.28
     gué
    0.28
     travelers
    0.27
    々木
    0.27
    \{\\
    0.26
     ACTS
    0.26
    Activations Density 1.078%

    No Known Activations