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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3557
    Prev
    Next
    INDEX
    Explanations

    references to spatial locations and their characteristics

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

    "location" or "locations"

    np_acts-logits-general · gemini-2.0-flash

    location of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.84
    StructEnd
    -0.76
    følgelig
    -0.63
    μως
    -0.61
    iastical
    -0.60
    WriteTagHelper
    -0.59
     /^[
    -0.59
     CreateTagHelper
    -0.59
     kierunku
    -0.58
     Ranks
    -0.58
    POSITIVE LOGITS
     Loc
    0.80
     Locations
    0.76
     locations
    0.73
     loc
    0.72
     getLocation
    0.72
     location
    0.68
    locations
    0.67
     Ubicación
    0.66
    Locations
    0.66
     spot
    0.65
    Activations Density 0.168%

    No Known Activations