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. 8650
    Prev
    Next
    INDEX
    Explanations

    issues related to software errors and crashing

    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
    Portály
    -0.95
    BeginContext
    -0.90
    DebuggerNonUser
    -0.74
    InputBorder
    -0.73
    ruptedException
    -0.72
     DBNull
    -0.70
    LLocation
    -0.68
    ELTS
    -0.67
     JpaRepository
    -0.66
     rospy
    -0.65
    POSITIVE LOGITS
     Tried
    0.51
    arius
    0.50
    heim
    0.48
    daging
    0.48
     Ground
    0.47
     kılı
    0.46
     dévelo
    0.46
    neri
    0.45
     tulisan
    0.44
    ときに
    0.44
    Activations Density 0.865%

    No Known Activations