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. 8969
    Prev
    Next
    INDEX
    Explanations

    expressions related to social justice and inequality

    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
    Personendaten
    -0.73
    __*/
    -0.68
    RegressionTest
    -0.64
    /$',
    -0.64
    <bos>
    -0.62
    rizona
    -0.61
    missible
    -0.58
    TargetException
    -0.58
    ensible
    -0.58
    IZONTAL
    -0.56
    POSITIVE LOGITS
     did
    2.08
     does
    1.89
     do
    1.72
    did
    1.69
    Did
    1.54
    does
    1.51
     Did
    1.48
    Does
    1.45
     Does
    1.42
     DID
    1.40
    Activations Density 0.194%

    No Known Activations