© 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. 39-GEMMASCOPE-RES-16K
    11. 4050
    Prev
    Next
    INDEX
    Explanations

    phrases and questions indicating a request for information or assistance

    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
    Something
    -0.84
     Something
    -0.83
    Anything
    -0.82
    something
    -0.80
     Anything
    -0.77
    Someone
    -0.76
     Someone
    -0.75
    somewhere
    -0.75
     Somebody
    -0.75
     Either
    -0.74
    POSITIVE LOGITS
     anty
    0.51
     ev
    0.51
     EconPapers
    0.50
     LITER
    0.45
     ay
    0.45
     eve
    0.44
     لينك
    0.42
     eser
    0.42
    Và
    0.41
     suon
    0.41
    Activations Density 0.353%

    No Known Activations