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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8718
    Prev
    Next
    INDEX
    Explanations

    comments expressing user feedback or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.47
    Moreover
    -0.47
    transQ
    -0.45
    Furthermore
    -0.43
    このように
    -0.43
     himſelf
    -0.42
    あるいは
    -0.40
     Moreover
    -0.39
     Furthermore
    -0.39
    のである
    -0.39
    POSITIVE LOGITS
     Been
    1.30
    Been
    1.27
     Seems
    1.10
     Didn
    1.03
     Gonna
    1.02
     haven
    1.02
     been
    1.02
     Got
    1.01
     got
    1.00
     Looks
    1.00
    Activations Density 0.801%

    No Known Activations