Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5611
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" and its variations in different 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
     sosial
    -0.58
     sociais
    -0.55
     sociale
    -0.55
     sociala
    -0.54
     sociales
    -0.54
    httphttps
    -0.52
     social
    -0.51
     sociali
    -0.49
     socialize
    -0.48
    -------
    -0.46
    POSITIVE LOGITS
     disant
    0.54
    journ
    0.46
    SBATCH
    0.45
    jour
    0.42
    WithMany
    0.41
     IERC
    0.41
     sánh
    0.40
    SharedCtor
    0.39
    tangentMode
    0.39
    borderSide
    0.38
    Activations Density 0.421%

    No Known Activations