© 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. 28-GEMMASCOPE-RES-16K
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    concepts related to data extraction and knowledge derivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Extracting information or inferences

    np_acts-logits-general · gemini-2.0-flash

    extracting or inferring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.59
    setts
    -0.43
    RTLR
    -0.42
     testSet
    -0.40
     broadcasters
    -0.40
    fflush
    -0.39
     Diſ
    -0.38
    WebServlet
    -0.38
    ertos
    -0.38
    broad
    -0.38
    POSITIVE LOGITS
     daraus
    0.87
     extracting
    0.86
     extract
    0.85
     extracted
    0.84
     extraer
    0.80
     extraction
    0.79
     Extract
    0.79
     therefrom
    0.78
    extract
    0.76
     Extraction
    0.75
    Activations Density 0.556%

    No Known Activations