© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2944
    Prev
    Next
    INDEX
    Explanations

    references to containment and concealment

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

    mentions of containers and their contents, particularly relating to illicit substances or evidence

    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
     Majefty
    -0.70
    addContainerGap
    -0.69
    Extinguishing
    -0.69
    tagHelperRunner
    -0.67
    DebuggerNonUser
    -0.67
    AxisAlignment
    -0.65
     تضيفلها
    -0.65
     scythe
    -0.63
    χρι
    -0.62
     jsPsych
    -0.61
    POSITIVE LOGITS
     mxArray
    0.54
    Inside
    0.53
     cage
    0.53
    INSIDE
    0.51
     Inside
    0.51
    psack
    0.51
     capsule
    0.50
    Autoritní
    0.50
    に入れ
    0.49
    taient
    0.48
    Activations Density 0.387%

    No Known Activations