© 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. 38-GEMMASCOPE-RES-16K
    11. 10045
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or governmental terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.68
    fjspx
    -0.56
    ValueGeneration
    -0.49
    verwijspagina
    -0.49
    RectangleBorder
    -0.47
    audiovisuel
    -0.42
    awtextra
    -0.41
    kuuta
    -0.41
    featureID
    -0.39
    ="@+
    -0.38
    POSITIVE LOGITS
     extremely
    0.94
     unlikely
    0.87
    extremely
    0.85
     irrelevant
    0.85
     extremamente
    0.84
     unavailable
    0.82
     unaffected
    0.81
     unclear
    0.81
     unchanged
    0.80
     sumamente
    0.80
    Activations Density 0.857%

    No Known Activations