© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 444
    Prev
    Next
    INDEX
    Explanations

    references to identical or duplicate entities and comparisons of their properties

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

    copying or duplication

    np_acts-logits-general · gemini-2.0-flash

    making identical copies

    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
    jsxFileName
    -0.52
     BorderSide
    -0.49
    InputBorder
    -0.48
    aarrggbb
    -0.47
    Mixer
    -0.46
    новништво
    -0.46
    zzleHttp
    -0.46
    󠁬
    -0.44
     geweest
    -0.44
    adone
    -0.44
    POSITIVE LOGITS
     replicated
    1.05
     replicate
    1.00
     identical
    0.99
     duplicate
    0.93
     copies
    0.91
     replication
    0.90
     duplicated
    0.88
     clone
    0.88
     copy
    0.88
     replicates
    0.87
    Activations Density 0.677%

    No Known Activations