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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11618
    Prev
    Next
    INDEX
    Explanations

    phrases that convey warnings or alerts regarding community behavior and norms

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

    highly frequent and semantically significant words that convey main themes or emphatic points in the text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    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
    '
    -1.57
     "
    -1.47
     '
    -1.43
    。"
    -1.23
    "'
    -1.05
    ."
    -1.05
    "
    -1.04
     ("
    -1.04
    ,"
    -1.03
    ..."
    -1.02
    POSITIVE LOGITS
     ‘
    1.83
    ’”
    1.73
    …’
    1.70
     “
    1.69
    (‘
    1.63
    ’)
    1.63
    ’
    1.63
    ’,
    1.63
    ’.”
    1.60
    .’”
    1.59
    Activations Density 9.659%

    No Known Activations