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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 10430
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and units of volume and concentration in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.68
    évaluateur
    -0.63
    +#+#
    -0.62
     ReactDOM
    -0.59
    ModelSerializer
    -0.59
    rungsseite
    -0.58
    ArrowToggle
    -0.58
    adaptiveStyles
    -0.57
    abinieri
    -0.55
    :✨
    -0.54
    POSITIVE LOGITS
     liter
    1.14
     liters
    1.11
     Lit
    1.08
     litres
    1.05
     litre
    1.03
    liter
    0.99
     Liter
    0.97
    Lit
    0.94
     LIT
    0.91
    liters
    0.91
    Activations Density 0.312%

    No Known Activations