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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6754
    Prev
    Next
    INDEX
    Explanations

    key elements of discussions or analyses related to companies and their standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    content related to discussions, articles, and shared insights from various sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.70
    Composable
    -0.68
    Kontrola
    -0.59
    iciais
    -0.59
     الرياضيه
    -0.57
     mAdapter
    -0.56
     विश्वसनीयता
    -0.56
     Waray
    -0.55
     ComVisible
    -0.54
    AccessFile
    -0.54
    POSITIVE LOGITS
     good
    0.84
     wonderful
    0.70
     fantastic
    0.69
     Good
    0.69
    good
    0.68
     great
    0.67
     bagus
    0.67
    Good
    0.65
     excellent
    0.63
     awesome
    0.63
    Activations Density 0.377%

    No Known Activations