© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5027
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to education and academic discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.51
    nan
    -0.50
     умова
    -0.50
    nal
    -0.46
    sizeCache
    -0.46
    nın
    -0.46
    nin
    -0.45
    nons
    -0.45
    OGND
    -0.44
    으로
    -0.44
    POSITIVE LOGITS
    uuuu
    0.74
    uuu
    0.71
    uuuuu
    0.64
    uu
    0.59
    ओं
    0.49
    u
    0.47
    ola
    0.44
    UUUU
    0.43
    o
    0.42
    hu
    0.41
    Activations Density 0.578%

    No Known Activations