© 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. 40-GEMMASCOPE-RES-16K
    6. 1566
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Jewish Star of David and references to Jewish identity or persecution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.49
    oredCriteria
    -0.46
     незавершена
    -0.44
     tiguan
    -0.43
    Captor
    -0.42
    oneofs
    -0.40
    ьаж
    -0.40
    WebElementEntity
    -0.40
    calipsis
    -0.40
    resave
    -0.40
    POSITIVE LOGITS
     star
    3.47
     Star
    3.17
    Star
    3.00
    star
    2.95
     stars
    2.92
     STAR
    2.75
     Stars
    2.67
    STAR
    2.59
    stars
    2.58
    Stars
    2.47
    Activations Density 1.344%

    No Known Activations