Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11201
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events related to political dynamics and territorial control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRIV
    -0.36
    Executable
    -0.32
     Púb
    -0.32
     hrd
    -0.30
    #
    -0.29
     rellen
    -0.29
    กรรม
    -0.28
     Procu
    -0.28
     flamen
    -0.28
     quidem
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.65
     Савезне
    0.65
    tagHelperRunner
    0.64
     Италијани
    0.64
     Italijanski
    0.64
    IsMutable
    0.63
     mergeFrom
    0.61
    expandindo
    0.60
    Diweddarwch
    0.59
     BorderSide
    0.59
    Activations Density 0.612%

    No Known Activations