© 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. 39-GEMMASCOPE-RES-16K
    11. 4518
    Prev
    Next
    INDEX
    Explanations

    references to honorific titles and the word "Honorable."

    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
     Dernière
    -0.39
    ########.
    -0.38
    ngOn
    -0.37
     compound
    -0.35
    
    -0.35
    gonic
    -0.35
    ineas
    -0.34
     compounded
    -0.34
    verne
    -0.34
     Duch
    -0.34
    POSITIVE LOGITS
    ored
    0.66
    oring
    0.63
    OGND
    0.60
    oured
    0.57
    setVerticalGroup
    0.53
    ours
    0.53
    orship
    0.51
    ORING
    0.50
    GEBURTS
    0.47
    ValueStyle
    0.47
    Activations Density 0.567%

    No Known Activations