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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7382
    Prev
    Next
    INDEX
    Explanations

    HTML structure elements, particularly within the `<html>` and `<head>` tags

    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
    hyrchwyd
    -0.53
    ņas
    -0.51
    évaluateur
    -0.51
     obyvateľov
    -0.44
    ondale
    -0.44
    mería
    -0.43
     Chong
    -0.42
    lankton
    -0.42
     Winston
    -0.41
    usercontent
    -0.41
    POSITIVE LOGITS
    ंदीखरीदारी
    1.04
    onViewCreated
    0.87
     viewDidLoad
    0.84
     nakalista
    0.78
    IsPostBack
    0.76
    head
    0.75
    Бахар
    0.73
    __()
    0.73
     BoxDecoration
    0.72
    expandindo
    0.72
    Activations Density 0.042%

    No Known Activations