© 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. 25-GEMMASCOPE-RES-16K
    11. 15421
    Prev
    Next
    INDEX
    Explanations

    references to personalized service and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recently
    -0.40
     particularly
    -0.37
     recent
    -0.35
     especially
    -0.35
    *}
    -0.31
     Blume
    -0.31
     obro
    -0.31
    try
    -0.30
     Dre
    -0.30
     juguete
    -0.30
    POSITIVE LOGITS
    ſelf
    0.81
     pleaſure
    0.77
    ſelves
    0.74
     ſche
    0.70
     faſt
    0.68
     Houſe
    0.68
    IsContent
    0.67
     Efq
    0.66
     ſhould
    0.65
     myſelf
    0.65
    Activations Density 0.214%

    No Known Activations