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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11299
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of pursuit or chasing

    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
    wrappers
    -0.29
     functioning
    -0.28
     sœurs
    -0.25
     الوا
    -0.24
     
    -0.23
     iné
    -0.23
     ausz
    -0.22
     pí
    -0.22
     меди
    -0.22
     capito
    -0.22
    POSITIVE LOGITS
     chase
    1.47
     chasing
    1.44
     chases
    1.30
    追
    1.30
     chased
    1.24
     pursuit
    1.20
     追
    1.20
     Follow
    1.18
    Follow
    1.15
     pursue
    1.14
    Activations Density 0.270%

    No Known Activations