© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 1562
    Prev
    Next
    INDEX
    Explanations

    content related to protests and violence, particularly in relation to cartoons depicting religious figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.82
     protoimpl
    -0.72
    +#+#
    -0.70
    UnknownFieldSet
    -0.67
    phosa
    -0.67
    +:+
    -0.66
     onCreateView
    -0.65
     Wicidata
    -0.65
    DockStyle
    -0.64
     nakalista
    -0.63
    POSITIVE LOGITS
     mocking
    0.67
     derogatory
    0.66
     insults
    0.64
     disrespectful
    0.62
     insulting
    0.60
     hurtful
    0.60
    失礼
    0.58
     dispar
    0.58
     rude
    0.57
     degrading
    0.57
    Activations Density 0.276%

    No Known Activations