© 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. 25-GEMMASCOPE-RES-16K
    11. 6824
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical presence or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.61
    PYX
    -0.60
    Chham
    -0.58
    mtrl
    -0.56
     invokingState
    -0.56
     tartalomajánló
    -0.55
    HandlerContext
    -0.54
    ScopeManager
    -0.53
    fromnode
    -0.53
    spiller
    -0.53
    POSITIVE LOGITS
     site
    1.20
     scene
    0.96
    site
    0.93
     premises
    0.87
     property
    0.76
     campus
    0.75
    scene
    0.74
     premise
    0.69
    premises
    0.68
    Site
    0.67
    Activations Density 0.231%

    No Known Activations