© 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 - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9842
    Prev
    Next
    INDEX
    Explanations

    phrases involving precision and exactness

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

    "exactly" followed by definite/relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    exact or precise description

    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
    ⓧ
    -0.72
    Autoritní
    -0.66
    Controllo
    -0.65
     pleaſure
    -0.64
     <<<<<<<<<<<<<<
    -0.64
    verständlich
    -0.62
     Psal
    -0.60
    getActiveSheet
    -0.60
    felves
    -0.59
    queryInterface
    -0.59
    POSITIVE LOGITS
     Exactly
    0.99
     exactly
    0.98
    Exactly
    0.94
     EXACTLY
    0.88
    exactly
    0.85
     same
    0.84
    precise
    0.79
     precisely
    0.79
     exac
    0.78
     exact
    0.78
    Activations Density 0.173%

    No Known Activations