© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11646
    Prev
    Next
    INDEX
    Explanations

    elements related to image processing metadata and attributes

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

    image URLs and file paths containing numeric identifiers and dimension parameters.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.59
     FetchType
    -0.56
     незавершена
    -0.55
    parsedMessage
    -0.54
    Portale
    -0.53
    GEBURTS
    -0.53
    RTLR
    -0.52
    تقاوى
    -0.52
    LookAnd
    -0.51
     queſta
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.48
     especialidad
    0.38
     Bestand
    0.38
    _
    0.35
     autrefois
    0.34
     Figueroa
    0.33
    SpringBootTest
    0.33
     vítima
    0.31
    ultados
    0.31
    GOTREF
    0.31
    Activations Density 0.411%

    No Known Activations