© 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. 38-GEMMASCOPE-RES-16K
    11. 14563
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or computational concepts, particularly in the context of fractional splines and their properties

    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
    GEBURTSDATUM
    -0.72
    MigrationBuilder
    -0.67
    Datuak
    -0.59
     '\\;'
    -0.58
     iprot
    -0.57
    UrlResolution
    -0.56
     Exacts
    -0.56
     мәкалә
    -0.53
     للمعارف
    -0.52
     beginnetje
    -0.52
    POSITIVE LOGITS
     support
    3.94
    support
    3.47
     Support
    3.42
    Support
    3.38
     SUPPORT
    3.34
     supports
    3.25
     supporting
    3.17
    SUPPORT
    3.09
    支持
    3.00
     supported
    2.91
    Activations Density 3.264%

    No Known Activations