© 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. 39-GEMMASCOPE-RES-16K
    6. 4767
    Prev
    Next
    INDEX
    Explanations

    references to specific cards and associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.43
    
    -0.42
     Италијани
    -0.40
     eventdata
    -0.38
    Xna
    -0.38
     eſſ
    -0.37
    gridy
    -0.36
    TypedDataSet
    -0.36
     zpě
    -0.36
     eſt
    -0.35
    POSITIVE LOGITS
     trick
    1.12
     tricks
    1.04
     Trick
    0.93
    trick
    0.90
     magic
    0.87
     magicians
    0.84
     magician
    0.84
     Tricks
    0.82
    Trick
    0.77
    tricks
    0.77
    Activations Density 0.152%

    No Known Activations