© 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. 5593
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and mathematical expressions

    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
     дописавши
    -0.26
    råd
    -0.26
     Autorisations
    -0.24
    bootstrapcdn
    -0.24
    onnaissance
    -0.24
    ReusableCell
    -0.23
     الحره
    -0.23
    spedes
    -0.23
    getMenuInflater
    -0.23
     Ehre
    -0.23
    POSITIVE LOGITS
     nine
    1.76
     Nine
    1.63
    9
    1.62
     NINE
    1.46
     ninth
    1.45
     nueve
    1.43
     девя
    1.41
     Ninth
    1.38
     ninety
    1.38
    nine
    1.38
    Activations Density 3.407%

    No Known Activations