© 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. 24-GEMMASCOPE-RES-16K
    11. 13598
    Prev
    Next
    INDEX
    Explanations

    numeric values or quantitative data related to processes and operations

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

    following types of inspections

    np_acts-logits-general · gemini-2.0-flash

    periodic inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.55
    LEncoder
    -0.55
    EDEFAULT
    -0.53
    WriteBarrier
    -0.52
     berea
    -0.50
    stopPropagation
    -0.50
    retung
    -0.48
    abestanden
    -0.47
    astify
    -0.46
    versies
    -0.45
    POSITIVE LOGITS
     inspection
    1.97
     Inspection
    1.82
     inspections
    1.78
     inspectors
    1.68
     inspecting
    1.66
     inspected
    1.63
    Inspection
    1.63
     Inspections
    1.61
     INSPECTION
    1.59
    inspection
    1.58
    Activations Density 0.227%

    No Known Activations