© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12811
    Prev
    Next
    INDEX
    Explanations

    specific terms related to doors, their mechanisms, and associated hardware in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonfire
    -0.57
     Picchu
    -0.56
    osomes
    -0.54
    heets
    -0.53
     tent
    -0.51
    tent
    -0.51
    XmlAccessType
    -0.50
    osomal
    -0.49
     tents
    -0.48
    xnn
    -0.48
    POSITIVE LOGITS
     hinges
    1.12
     latch
    0.93
     handle
    0.93
     handles
    0.91
     door
    0.90
     hinge
    0.87
     knobs
    0.86
     locks
    0.85
     knob
    0.82
     Handle
    0.82
    Activations Density 0.141%

    No Known Activations