Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2818
    Prev
    Next
    INDEX
    Explanations

    phrases related to a sense of discontent with societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UIControlState
    -0.86
     poffe
    -0.79
     uſed
    -0.76
    بوابة
    -0.74
     ſtand
    -0.73
     fhew
    -0.72
    ArgsConstructor
    -0.71
    ſelf
    -0.71
     pleaſure
    -0.71
     diſt
    -0.70
    POSITIVE LOGITS
     @
    0.67
     Anonymous
    0.66
     Mr
    0.66
     j
    0.64
    Mr
    0.61
     anonymous
    0.61
    Anonymous
    0.57
     k
    0.56
    anon
    0.56
    @
    0.54
    Activations Density 0.175%

    No Known Activations