© 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. 5184
    Prev
    Next
    INDEX
    Explanations

    common phrases and structures related to sports or competition

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

    ordinal numbers and rankings (e.g., "sixth," "third," "largest," "consecutive").

    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
     estekak
    -0.55
    AutoresizingMask
    -0.53
    +#+#
    -0.52
    erapeutics
    -0.50
    chemise
    -0.48
    iastes
    -0.47
    RenderAtEndOf
    -0.45
    ########.
    -0.43
    exitRule
    -0.43
     <<<<<<<<<<<<<<
    -0.43
    POSITIVE LOGITS
     fifth
    2.75
     fourth
    2.70
     sixth
    2.64
     seventh
    2.61
     ninth
    2.47
     third
    2.42
     eighth
    2.41
    fifth
    2.25
     tenth
    2.20
    fourth
    2.20
    Activations Density 0.685%

    No Known Activations