© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1279
    Prev
    Next
    INDEX
    Explanations

    technical aspects of semiconductor technology and related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lightboxes
    -0.70
    sizeCache
    -0.65
    LEncoder
    -0.63
     actionMode
    -0.62
     ModelExpression
    -0.62
     CURIAM
    -0.60
    GetAxis
    -0.59
     NSCoder
    -0.59
    ftagPool
    -0.58
     bezeichneter
    -0.58
    POSITIVE LOGITS
     itself
    1.01
     selve
    0.90
     eigentlichen
    0.90
    itself
    0.85
     proprement
    0.84
     samot
    0.84
     eigentliche
    0.84
     themselves
    0.80
     core
    0.75
    本身
    0.74
    Activations Density 0.726%

    No Known Activations