© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    references to the Southern region, its entities, and related concepts

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

    the word "Southern" in various contexts.

    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
    PickerController
    -0.38
     Dug
    -0.32
     cancha
    -0.31
     déf
    -0.31
     huelga
    -0.30
     tambor
    -0.30
    glicher
    -0.29
    makeConstraints
    -0.29
     trigo
    -0.28
     ändå
    -0.28
    POSITIVE LOGITS
     فريبيس
    0.77
    mergeFrom
    0.68
     oprot
    0.66
    Diwedd
    0.63
    parsedMessage
    0.58
    stylers
    0.53
    setVerticalGroup
    0.52
    providedIn
    0.52
    AccessFile
    0.52
    SBATCH
    0.51
    Activations Density 0.173%

    No Known Activations