© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2292
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and conjunctions that indicate additional information or further elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.70
     zwiſchen
    -0.68
    iſchen
    -0.66
    "}")
    -0.66
    ſſung
    -0.66
    iſche
    -0.65
     geſch
    -0.63
    <unused71>
    -0.63
    <unused51>
    -0.63
    [@BOS@]
    -0.63
    POSITIVE LOGITS
     informée
    0.52
     associated
    0.35
    ,
    0.34
     engaging
    0.32
     given
    0.31
    ospatial
    0.31
     Censo
    0.31
    addContainerGap
    0.30
     aroused
    0.29
     engages
    0.29
    Activations Density 0.458%

    No Known Activations