© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and environmental features

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

    spatial location descriptions in natural environments, particularly forests and wooded areas.

    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
    +#+
    -0.51
    WithIOException
    -0.50
    Autoritní
    -0.45
    OGND
    -0.43
     الاطلاع
    -0.41
     épis
    -0.41
     Económica
    -0.39
    routeProvider
    -0.38
    Havolalar
    -0.36
     actionMode
    -0.35
    POSITIVE LOGITS
     forest
    2.25
     forests
    2.16
    forest
    1.88
     Forest
    1.77
     forested
    1.74
    forests
    1.74
     Forests
    1.73
     woods
    1.73
     woodland
    1.69
    Forest
    1.67
    Activations Density 0.369%

    No Known Activations