© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6092
    Prev
    Next
    INDEX
    Explanations

    references to time intervals and measurements

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

    time measurements

    np_acts-logits-general · gemini-2.0-flash

    time units and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.64
    TextBoxColumn
    -0.52
    closedir
    -0.52
     {?>
    -0.51
    /**
    -0.50
    йн
    -0.49
     superiori
    -0.49
    ">//
    -0.48
    SourceChecksum
    -0.47
     inter
    -0.47
    POSITIVE LOGITS
    findpost
    0.90
    getMinutes
    0.84
     Hours
    0.82
     HOURS
    0.82
    DockStyle
    0.76
    parsedMessage
    0.75
     useStyles
    0.74
     AssemblyCulture
    0.74
     hours
    0.74
     increments
    0.74
    Activations Density 0.351%

    No Known Activations