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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1604
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to scientific and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.37
    createClass
    -0.35
     المعيارى
    -0.34
    licola
    -0.33
     shots
    -0.33
     cheminée
    -0.31
     mixtape
    -0.31
    fromnode
    -0.30
    kennung
    -0.30
    肉
    -0.30
    POSITIVE LOGITS
    DoubleQuotes
    0.62
     étoit
    0.56
     <=",
    0.54
     auroit
    0.54
    RectangleBorder
    0.54
     étoient
    0.53
    RTLU
    0.53
     avoient
    0.53
    jsxFileName
    0.52
     surla
    0.52
    Activations Density 0.456%

    No Known Activations