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. 18-GEMMASCOPE-RES-16K
    6. 10086
    Prev
    Next
    INDEX
    Explanations

    statements related to systemic injustice and societal critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     EconPapers
    -0.89
    aarrggbb
    -0.85
    httphttps
    -0.79
     &___
    -0.79
    HasAnnotation
    -0.76
    LookAnd
    -0.74
     Meksiku
    -0.74
     Савезне
    -0.73
    TypedDataSet
    -0.72
    verwijspagina
    -0.71
    POSITIVE LOGITS
    <eos>
    0.80
    ↵↵
    0.75
    なお
    0.53
    </tr>
    0.53
    </h3>
    0.52
    ↵↵↵
    0.52
    ↵
    0.47
     Bonus
    0.46
    ________________
    0.46
    ↵↵↵↵↵
    0.46
    Activations Density 0.053%

    No Known Activations