© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15426
    Prev
    Next
    INDEX
    Explanations

    discussions about game mechanics and script modifications

    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
     ModelExpression
    -0.43
    IsContent
    -0.41
     communication
    -0.38
     preocupado
    -0.37
     communications
    -0.36
     tâches
    -0.35
     expressed
    -0.33
     TextInputType
    -0.33
     незавершена
    -0.33
     charges
    -0.32
    POSITIVE LOGITS
     modded
    0.93
     modding
    0.78
     mods
    0.75
     remastered
    0.64
     bugged
    0.62
     Mods
    0.59
    自制
    0.57
    patched
    0.56
     custom
    0.56
     remaster
    0.56
    Activations Density 0.507%

    No Known Activations