© 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. 39-GEMMASCOPE-RES-16K
    11. 2962
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical objects, particularly those with specific attributes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     povr
    -0.35
     tark
    -0.35
     okolí
    -0.35
     évolu
    -0.33
     vrst
    -0.33
    fieldId
    -0.32
     liefer
    -0.32
    latin
    -0.31
     derro
    -0.31
     halus
    -0.31
    POSITIVE LOGITS
     facing
    1.41
     pointing
    1.24
    facing
    1.13
     Facing
    1.10
    Facing
    1.06
     pointed
    1.05
     angled
    0.96
    pointing
    0.96
     faced
    0.94
     tilted
    0.88
    Activations Density 0.769%

    No Known Activations