© 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. 24-GEMMASCOPE-RES-16K
    6. 7669
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data or quantified information

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

    that start conditional clauses

    np_acts-logits-general · gemini-2.0-flash

    clause starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     but
    -1.21
     therefore
    -1.21
     entanto
    -1.13
    Поэтому
    -1.08
     hence
    -1.07
     however
    -1.03
     thus
    -1.01
    μως
    -1.00
     moreover
    -0.99
     furthermore
    -0.99
    POSITIVE LOGITS
    Although
    0.81
    While
    0.79
     Although
    0.79
    When
    0.78
    Since
    0.77
     Since
    0.76
     While
    0.75
    正如
    0.75
     Unlike
    0.74
     Despite
    0.74
    Activations Density 0.447%

    No Known Activations