© 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. 22-GEMMASCOPE-RES-16K
    6. 15237
    Prev
    Next
    INDEX
    Explanations

    physical structures and their spatial relationships within environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.64
    styleable
    -0.47
    findpost
    -0.45
    뇨
    -0.43
    addTab
    -0.41
    toHaveBeen
    -0.39
    jetbrains
    -0.39
    medriver
    -0.39
    TagMode
    -0.39
     SwitchCompat
    -0.38
    POSITIVE LOGITS
     wall
    1.14
     walls
    0.95
     WALL
    0.92
    壁
    0.88
     mural
    0.88
    Wall
    0.88
     parede
    0.88
    wall
    0.88
     murales
    0.87
     Wall
    0.86
    Activations Density 0.330%

    No Known Activations