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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 110798
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical analysis and data synthesis in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.51
    ReusableCell
    -0.44
     surla
    -0.44
     achtergrond
    -0.42
     cucchiaio
    -0.40
    Shelf
    -0.39
    GEBURTS
    -0.38
     prate
    -0.38
    FunctionFlags
    -0.38
    StoryboardSegue
    -0.37
    POSITIVE LOGITS
    SharedCtor
    0.53
     kasarigan
    0.49
    ">//
    0.45
     initComponents
    0.44
    統一
    0.41
     consolidated
    0.41
    AutoScaleMode
    0.41
     "..\..\..\
    0.40
    ChildScrollView
    0.40
     برانيه
    0.40
    Activations Density 0.221%

    No Known Activations