© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27307
    Prev
    Next
    INDEX
    Explanations

    commands and references related to climbing activities

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

    climbing in

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     cons
    -0.54
    PlaceHolder
    -0.51
     purpose
    -0.51
     berlaku
    -0.50
    nani
    -0.50
    _->
    -0.49
    odis
    -0.49
    HttpStatus
    -0.47
     bạc
    -0.47
     introduces
    -0.47
    POSITIVE LOGITS
     climbing
    1.40
    climbing
    1.38
     Climbing
    1.37
     climbers
    1.32
     climber
    1.31
     climb
    1.30
     crawling
    1.27
    climb
    1.26
     Climb
    1.25
     crawl
    1.24
    Activations Density 0.033%

    No Known Activations