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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 873
    Prev
    Next
    INDEX
    Explanations

    references to historical events and periods

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

    Plural form of years or decades

    np_acts-logits-general · gemini-2.0-flash

    numerical decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     Jiao
    -0.34
    稽
    -0.34
     inoculation
    -0.34
     Receiving
    -0.33
     Execution
    -0.33
     Electoral
    -0.32
    ercise
    -0.31
    pvc
    -0.31
     opr
    -0.31
    acuation
    -0.31
    POSITIVE LOGITS
    Portály
    0.72
     Jahrhundert
    0.71
    century
    0.69
    sizeCache
    0.68
    AnchorStyles
    0.67
    decade
    0.64
     betweenstory
    0.63
     heyday
    0.62
     century
    0.61
    Century
    0.61
    Activations Density 0.185%

    No Known Activations