© 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. 38-GEMMASCOPE-RES-16K
    6. 9942
    Prev
    Next
    INDEX
    Explanations

    terms related to image processing and signal generation

    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
    HasColumnType
    -0.34
    сылкі
    -0.30
    ∭
    -0.28
     Photocase
    -0.28
    ณ์
    -0.26
    눠
    -0.26
     Erbe
    -0.26
    ampilan
    -0.25
    ReadKey
    -0.24
    CodedInputStream
    -0.24
    POSITIVE LOGITS
     generating
    2.94
     generation
    2.94
     generate
    2.89
     generated
    2.80
     Generate
    2.73
     Generating
    2.72
     Generation
    2.67
     generator
    2.67
     GENER
    2.67
     generates
    2.66
    Activations Density 1.436%

    No Known Activations