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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 674
    Prev
    Next
    INDEX
    Explanations

    discussions about societal responsibility and the effects of long-term exclusion and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows prepositions

    np_acts-logits-general · gemini-2.0-flash

    society and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.49
     Faithful
    -0.47
     teasing
    -0.47
     Gateway
    -0.46
     recenti
    -0.46
     colegas
    -0.45
     legenda
    -0.45
     حرفه
    -0.45
     rito
    -0.45
    尴尬
    -0.45
    POSITIVE LOGITS
     society
    0.98
     societies
    0.96
     societal
    0.91
     governments
    0.90
     humans
    0.88
     civilization
    0.87
     humanity
    0.86
     mankind
    0.85
     human
    0.84
     social
    0.84
    Activations Density 0.901%

    No Known Activations