© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6863
    Prev
    Next
    INDEX
    Explanations

    terms related to perception and sensory experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oner
    -0.58
     transfieras
    -0.57
    DispatchToProps
    -0.56
    /**
    -0.54
    tahankan
    -0.53
     trilha
    -0.53
     abzu
    -0.52
     felice
    -0.52
     /\.(
    -0.52
     equator
    -0.52
    POSITIVE LOGITS
     sight
    1.17
     seeing
    1.13
     viewing
    1.03
    seeing
    1.03
     seen
    1.00
     Sight
    0.99
     watching
    0.96
    Seen
    0.95
    sight
    0.93
     view
    0.92
    Activations Density 0.320%

    No Known Activations