© 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. 18-GEMMASCOPE-RES-16K
    11. 3935
    Prev
    Next
    INDEX
    Explanations

    references to various laboratories and their associated environments or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Locations: garages, laboratories, kitchens

    np_acts-logits-general · gemini-2.0-flash

    locations and their associated objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.77
    Datuak
    -0.74
     disambiguazione
    -0.73
    bootstrapcdn
    -0.70
     AssemblyProduct
    -0.69
    UnsafeEnabled
    -0.67
    protoimpl
    -0.66
    CPtr
    -0.64
    UseVisualStyle
    -0.64
    IsMutable
    -0.62
    POSITIVE LOGITS
     floor
    0.78
     walls
    0.68
     located
    0.64
     environment
    0.63
     environments
    0.61
    Entrance
    0.60
     facilities
    0.60
     entrance
    0.59
    floor
    0.59
     complexes
    0.58
    Activations Density 0.642%

    No Known Activations