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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9547
    Prev
    Next
    INDEX
    Explanations

    elements related to processes and formal requirements in transactional contexts

    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
     protoimpl
    -0.69
    oredCriteria
    -0.66
     FetchType
    -0.65
    tanleria
    -0.65
     utafitiHapana
    -0.64
     Biôgrafia
    -0.61
    Jereo
    -0.59
    DebuggerNonUser
    -0.57
    AddTagHelper
    -0.56
    MessageTagHelper
    -0.56
    POSITIVE LOGITS
     within
    3.16
     Within
    2.95
    Within
    2.94
    within
    2.93
     WITHIN
    2.59
     innerhalb
    2.07
     binnen
    1.89
     entro
    1.68
     inom
    1.68
     dentro
    1.65
    Activations Density 0.833%

    No Known Activations