© 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. 16-GEMMASCOPE-RES-16K
    6. 13092
    Prev
    Next
    INDEX
    Explanations

    references to a logging framework or messaging system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.77
    OGND
    -0.73
    Tikang
    -0.69
    ValueStyle
    -0.64
    WriteTagHelper
    -0.63
    StructEnd
    -0.61
    ########.
    -0.60
    URLException
    -0.60
     IBOutlet
    -0.60
     Chwiliwch
    -0.59
    POSITIVE LOGITS
    Slf
    0.85
    getLogger
    0.75
     ILogger
    0.74
    logrus
    0.73
    Logger
    0.70
    ILogger
    0.68
    LoggerFactory
    0.67
    logger
    0.66
     Logger
    0.60
    slf
    0.59
    Activations Density 0.123%

    No Known Activations