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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4119
    Prev
    Next
    INDEX
    Explanations

    terms related to political and legal accountability

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

    negation, dismissal, or invalidity

    np_acts-logits-general · gemini-2.0-flash

    legal terminology and technical terms

    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
    gste
    -0.52
    abestanden
    -0.51
     trăm
    -0.50
     captives
    -0.50
     SQLITE
    -0.50
     geek
    -0.49
     Elder
    -0.48
     LSTM
    -0.48
     mythology
    -0.48
     captures
    -0.48
    POSITIVE LOGITS
     Autorisations
    0.58
    ArgsConstructor
    0.51
    HasForeignKey
    0.50
    cense
    0.50
     BoxFit
    0.50
    addContainerGap
    0.49
    writeField
    0.48
     design
    0.48
     AssemblyProduct
    0.47
    twimg
    0.46
    Activations Density 0.036%

    No Known Activations