© 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. 1-GEMMASCOPE-RES-16K
    6. 8749
    Prev
    Next
    INDEX
    Explanations

    negative numbers or other mathematical expressions that include negative symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pfarrer
    -0.44
     Erziehung
    -0.41
     Zusammensetzung
    -0.41
     desar
    -0.40
     Vorbereitung
    -0.38
     Pferd
    -0.38
     Verein
    -0.38
     Unterschiede
    -0.37
     Erweiterung
    -0.37
    ínű
    -0.37
    POSITIVE LOGITS
     (-
    2.23
    (-
    2.06
     $(-
    1.90
     [-
    1.86
    [-
    1.73
     (−
    1.68
    }(-
    1.67
    =(-
    1.62
    {(-
    1.56
     $[-
    1.55
    Activations Density 0.328%

    No Known Activations