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. 16-GEMMASCOPE-RES-16K
    6. 1441
    Prev
    Next
    INDEX
    Explanations

    activities and elements related to climbing or ascending

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

    Mentions climbing and heights

    np_acts-logits-general · gemini-2.0-flash

    reaching the summit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.81
    tagHelperRunner
    -0.76
    complexContent
    -0.73
    windowFixed
    -0.67
    parsedMessage
    -0.65
    hmig
    -0.62
    RenderAtEndOf
    -0.61
    \{\\
    -0.61
    torta
    -0.60
    цездатний
    -0.60
    POSITIVE LOGITS
     balcony
    0.64
     balcón
    0.61
     summit
    0.61
    ⓘ
    0.60
     above
    0.58
    above
    0.58
     sommet
    0.57
     climbing
    0.57
     ascended
    0.57
     stair
    0.57
    Activations Density 0.242%

    No Known Activations