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. 14503
    Prev
    Next
    INDEX
    Explanations

    references to urban development projects and their attributes

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

    construction or development projects

    np_acts-logits-general · gemini-2.0-flash

    large development 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
     المعيارى
    -0.75
     препратки
    -0.73
    AnchorTagHelper
    -0.60
     pinulongan
    -0.58
    ThroughAttribute
    -0.53
     LCCN
    -0.52
    AxisAlignment
    -0.52
     couch
    -0.51
    MigrationBuilder
    -0.51
    aarrggbb
    -0.50
    POSITIVE LOGITS
     project
    1.02
     Phase
    0.90
     planned
    0.89
     phase
    0.86
     construction
    0.85
    Phase
    0.84
     completion
    0.82
     envisioned
    0.82
     строительство
    0.81
     development
    0.80
    Activations Density 0.373%

    No Known Activations