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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 1406
    Prev
    Next
    INDEX
    Explanations

    mentions of properties and their characteristics, particularly related to security features and neighborhood dynamics

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

    streets, roads, and neighborhoods

    np_acts-logits-general · gemini-2.0-flash

    neighborhoods and blocks

    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
    fung
    -0.59
    Terminal
    -0.55
     Terminal
    -0.50
     invokingState
    -0.49
    argout
    -0.49
    UMBIA
    -0.49
     desk
    -0.48
    asgi
    -0.48
    BarButtonItem
    -0.48
     convention
    -0.48
    POSITIVE LOGITS
     neighborhood
    1.34
     neighbourhood
    1.24
     neighbors
    1.19
     Neighborhood
    1.17
    neighborhood
    1.17
     neighbours
    1.16
    Neighborhood
    1.13
     NEIGH
    1.12
     homeowners
    1.12
     neighbor
    1.07
    Activations Density 0.167%

    No Known Activations