© 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. 35-GEMMASCOPE-RES-16K
    6. 7923
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political opposition and support for controversial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raszam
    -0.49
    raszamy
    -0.49
     createState
    -0.45
    InputBorder
    -0.41
    effetto
    -0.41
     riuscito
    -0.40
    ismet
    -0.40
     réussir
    -0.40
    occasione
    -0.40
     împre
    -0.39
    POSITIVE LOGITS
     abortion
    0.64
     polyg
    0.63
     homosexuality
    0.62
     abol
    0.60
     legalization
    0.59
     socialism
    0.58
     gay
    0.58
     banning
    0.57
     vegetarian
    0.56
    gay
    0.56
    Activations Density 0.884%

    No Known Activations