© 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. 22-GEMMASCOPE-RES-16K
    11. 5842
    Prev
    Next
    INDEX
    Explanations

    code structures indicating method definitions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.09
    ſcher
    -0.93
    majánló
    -0.88
     ब्रेकडाउन
    -0.84
     ContentValues
    -0.84
    featureID
    -0.84
     ſche
    -0.83
    parsedMessage
    -0.82
     témoig
    -0.82
    ſchaft
    -0.81
    POSITIVE LOGITS
        
    0.60
    1
    0.60
    ↵
    0.59
    0
    0.57
    (
    0.55
    [toxicity=0]
    0.54
     I
    0.54
      
    0.52
     The
    0.52
    2
    0.52
    Activations Density 0.165%

    No Known Activations