© 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. 5451
    Prev
    Next
    INDEX
    Explanations

    the word "an" in varying contexts

    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
    étoit
    -0.72
    égard
    -0.61
    épaisseur
    -0.59
     varandra
    -0.57
    attendre
    -0.57
    écoute
    -0.56
    assemblée
    -0.56
    occupe
    -0.55
    attente
    -0.54
    autonomie
    -0.54
    POSITIVE LOGITS
     assortment
    0.79
     array
    0.79
     entire
    0.77
     excellent
    0.71
     example
    0.70
     important
    0.69
     impressive
    0.69
     actual
    0.68
     idea
    0.68
     army
    0.68
    Activations Density 0.235%

    No Known Activations