© 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. 12665
    Prev
    Next
    INDEX
    Explanations

    phrases indicating arrival and observation of circumstances surrounding significant events

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

    temporal sequences of events and narrative progression through time.

    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
    </tfoot>
    -0.40
    jasama
    -0.34
    JsonInclude
    -0.34
     boletín
    -0.32
     Ehe
    -0.32
    Viitteet
    -0.32
    oa̍t
    -0.31
    想去
    -0.31
     exportación
    -0.30
    了出去
    -0.30
    POSITIVE LOGITS
     arrived
    2.95
     arrival
    2.95
     arrive
    2.94
     arriving
    2.92
     arrives
    2.81
     Arrival
    2.64
    Arri
    2.61
     Arrived
    2.53
     arrivals
    2.53
    arrival
    2.52
    Activations Density 0.414%

    No Known Activations