© 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. 3-GEMMASCOPE-RES-16K
    11. 8920
    Prev
    Next
    INDEX
    Explanations

    starts of paragraphs or new sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.61
    <bos>
    -1.57
     surla
    -1.40
     للاسماء
    -1.39
    tagHelperRunner
    -1.36
    AddTagHelper
    -1.30
     ब्रेकडाउन
    -1.29
    parsedMessage
    -1.27
     autorytatywna
    -1.26
     Савезне
    -1.25
    POSITIVE LOGITS
    '
    0.57
    ’
    0.57
    <eos>
    0.50
     her
    0.47
     we
    0.47
     he
    0.45
     
    0.45
    (
    0.45
     so
    0.45
     "
    0.42
    Activations Density 17.610%

    No Known Activations