Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16022
    Prev
    Next
    INDEX
    Explanations

    references to necessity or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſehen
    -0.70
     ſind
    -0.66
     EconPapers
    -0.64
     للاسماء
    -0.64
     queſta
    -0.63
     ſei
    -0.63
     beſch
    -0.63
    ImageContext
    -0.63
     imagui
    -0.60
     Picchu
    -0.60
    POSITIVE LOGITS
     reluctance
    0.49
     tendency
    0.49
     ability
    0.49
     penchant
    0.49
     Fähigkeit
    0.46
     reliance
    0.46
     willingness
    0.45
     unwillingness
    0.45
     inability
    0.44
     desire
    0.44
    Activations Density 0.355%

    No Known Activations