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. 13-GEMMASCOPE-RES-16K
    6. 11919
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to measurement and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.69
     betweenstory
    -0.60
     MonoBehaviour
    -0.59
    例句
    -0.54
    esez
    -0.53
    즉
    -0.52
    󠁮
    -0.51
     emf
    -0.51
     Unwin
    -0.51
    ObjectId
    -0.51
    POSITIVE LOGITS
     protoimpl
    0.64
     виправивши
    0.63
    twimg
    0.53
    Exceeded
    0.52
     wild
    0.51
    なもの
    0.51
     ones
    0.49
     intStringLen
    0.49
     none
    0.48
     involve
    0.48
    Activations Density 1.020%

    No Known Activations