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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6594
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to image processing and machine learning architectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bakgrunnsstoff
    -0.40
    yntaxException
    -0.38
     stability
    -0.37
     Pingback
    -0.36
    angliski
    -0.36
    ∎
    -0.36
    MSD
    -0.35
     neer
    -0.35
     Inorg
    -0.34
     preds
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    0.60
     estekak
    0.60
    WebpackPlugin
    0.57
     DataLoader
    0.57
    jsxFileName
    0.55
     المعيارى
    0.53
    DispatchToProps
    0.51
     torchvision
    0.50
    dataset
    0.49
    Dataset
    0.49
    Activations Density 0.510%

    No Known Activations