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. 21-GEMMASCOPE-RES-16K
    6. 7472
    Prev
    Next
    INDEX
    Explanations

    non-verbal characters or formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]}"
    -0.76
    깥
    -0.72
     transfieras
    -0.70
    此
    -0.65
     jedoch
    -0.65
     Após
    -0.65
    קב
    -0.64
     poiché
    -0.61
    此处
    -0.60
    也可
    -0.60
    POSITIVE LOGITS
     somebody
    0.89
     So
    0.85
    somebody
    0.82
     Somebody
    0.81
    Everybody
    0.79
    Somebody
    0.79
     everybody
    0.79
     And
    0.78
     Everybody
    0.77
     Yeah
    0.77
    Activations Density 0.132%

    No Known Activations