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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12947
    Prev
    Next
    INDEX
    Explanations

    measurement units related to biochemical concentrations

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

    Values with units (e.g., µg/mL, pmol/L)

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    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
     double
    -0.55
     hypo
    -0.53
     Pi
    -0.52
     pi
    -0.50
     “
    -0.49
    EME
    -0.49
     command
    -0.48
     word
    -0.47
     break
    -0.47
     Lab
    -0.46
    POSITIVE LOGITS
    ArrowToggle
    0.86
     متعلقه
    0.84
     auroit
    0.81
    principalTable
    0.80
     Efq
    0.79
     NSCoder
    0.79
    клопе
    0.78
     hâte
    0.77
    లాలు
    0.76
     Drapeau
    0.75
    Activations Density 0.298%

    No Known Activations