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. 994
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations or landmarks

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

    airplane or boat landings

    np_acts-logits-general · gemini-2.0-flash

    landing, docks, runways

    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
    tvguidetime
    -0.56
     ddelweddau
    -0.54
    posables
    -0.45
    hio
    -0.44
     تانيه
    -0.44
     ***!
    -0.43
     content
    -0.43
     unterwegs
    -0.42
    tauan
    -0.42
    JspWriter
    -0.41
    POSITIVE LOGITS
     dock
    1.09
     wharf
    1.03
     docks
    1.02
     runway
    1.01
     docking
    0.96
     runways
    0.92
     jetty
    0.88
     landing
    0.82
     Landing
    0.80
     Dock
    0.78
    Activations Density 0.145%

    No Known Activations