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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12835
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement and animals, particularly concerning wildlife management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.52
    BagConstraints
    -0.46
    delà
    -0.44
    twimg
    -0.43
    opress
    -0.42
    rrggbb
    -0.42
    strzy
    -0.42
     emergencia
    -0.42
    Geplaatst
    -0.41
    uxxxx
    -0.41
    POSITIVE LOGITS
     roaming
    1.56
     roam
    1.46
     wandering
    1.42
     wander
    1.37
     wanders
    1.28
     wandered
    1.26
     roving
    1.25
     circulate
    1.18
     walking
    1.15
     strolling
    1.15
    Activations Density 0.397%

    No Known Activations