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. 1995
    Prev
    Next
    INDEX
    Explanations

    terms related to support services for victims of domestic and sexual violence

    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
    enterOuterAlt
    -0.80
    InputBorder
    -0.71
    </tfoot>
    -0.70
    ValueStyle
    -0.67
    Datuak
    -0.66
     الرياضيه
    -0.64
     autorytatywna
    -0.59
    VIAF
    -0.58
     retirees
    -0.57
     snippetHide
    -0.57
    POSITIVE LOGITS
     victim
    1.51
     victims
    1.43
     Victim
    1.36
     Victims
    1.34
     rape
    1.26
    victim
    1.23
     violence
    1.22
     abuse
    1.22
     domestic
    1.21
    Victim
    1.20
    Activations Density 0.210%

    No Known Activations