© 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. 14-GEMMASCOPE-RES-16K
    11. 7926
    Prev
    Next
    INDEX
    Explanations

    statistical percentages and participation rates in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    careous
    -0.35
     fluctuation
    -0.29
     svå
    -0.29
    之后
    -0.28
    makeText
    -0.28
     noticeable
    -0.27
    personality
    -0.27
     desemple
    -0.27
     dull
    -0.27
     vag
    -0.26
    POSITIVE LOGITS
    Personendaten
    0.72
    dafx
    0.66
    Дереккөздер
    0.65
    GEBURTSDATUM
    0.64
     OFDb
    0.63
     Normdatei
    0.61
    Vidite
    0.60
    oredCriteria
    0.60
    fjspx
    0.59
    новниш
    0.57
    Activations Density 0.504%

    No Known Activations