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. 21-GEMMASCOPE-RES-16K
    6. 697
    Prev
    Next
    INDEX
    Explanations

    code imports and semicolon-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =
    -0.48
    曖昧さ回避
    -0.48
    那个
    -0.47
    enden
    -0.46
    那個
    -0.45
     =
    -0.45
    הערות
    -0.45
    ritsar
    -0.44
    GetMapping
    -0.43
    $("#
    -0.43
    POSITIVE LOGITS
    PerformLayout
    1.11
    NameInMap
    1.01
     autorytatywna
    1.00
    Personensuche
    0.87
    RectangleBorder
    0.85
    BeginContext
    0.85
    bootstrapcdn
    0.84
    MemoryWarning
    0.83
     bezeichneter
    0.82
    IUrlHelper
    0.81
    Activations Density 0.039%

    No Known Activations