© 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. 13319
    Prev
    Next
    INDEX
    Explanations

    content related to financial transactions and assessments

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

    emphatic or intensifying language that conveys strong emotion or certainty.

    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
     very
    -1.57
     extremely
    -1.38
     highly
    -1.30
    かなり
    -1.28
     greatly
    -1.26
     muy
    -1.25
     bardzo
    -1.25
     molto
    -1.24
     très
    -1.23
     очень
    -1.23
    POSITIVE LOGITS
    Искәрмәләр
    0.47
    rungsseite
    0.42
     poffible
    0.38
     jemanden
    0.38
    Somewhere
    0.36
     SOMEONE
    0.36
    somewhere
    0.35
     somebody
    0.35
     tanong
    0.35
     POSSIBLE
    0.35
    Activations Density 1.717%

    No Known Activations