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. 12-GEMMASCOPE-RES-16K
    6. 4436
    Prev
    Next
    INDEX
    Explanations

    topics related to technology and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arschu
    -0.49
     Er
    -0.48
     er
    -0.48
     save
    -0.46
    holm
    -0.46
    ob
    -0.45
    NewGuid
    -0.45
     skal
    -0.45
    ifon
    -0.45
     Mr
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.79
    ſelf
    0.78
     houſe
    0.77
    DockStyle
    0.75
     ejus
    0.74
    قایناقلار
    0.73
     ingår
    0.70
     Majefty
    0.69
     poffe
    0.69
    balleur
    0.68
    Activations Density 0.808%

    No Known Activations