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. 18-GEMMASCOPE-RES-16K
    6. 483
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and architectural processes

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

    the word "construction"

    np_acts-logits-general · gemini-2.0-flash

    construction industry and projects

    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
     <<<<<<<<<<<<<<
    -0.68
    tvguidetime
    -0.68
     /\.
    -0.65
    WaitGroup
    -0.62
    windowFixed
    -0.61
    thenReturn
    -0.59
    antMatchers
    -0.57
     HasFactory
    -0.57
     imageNamed
    -0.57
     Lyt
    -0.56
    POSITIVE LOGITS
    builds
    0.74
    build
    0.72
    BUILD
    0.72
     BUILD
    0.72
     build
    0.72
     Build
    0.70
     stringBuilder
    0.67
     constr
    0.66
     Builders
    0.63
    builders
    0.63
    Activations Density 0.226%

    No Known Activations