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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15195
    Prev
    Next
    INDEX
    Explanations

    elements related to data organization, documentation, and communication of updates

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

    after "the"

    np_acts-logits-general · gemini-2.0-flash

    associated or accompanying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.46
     pinulongan
    -0.46
    XmlType
    -0.46
    ್
    -0.43
    Produzione
    -0.43
    ActionTypes
    -0.41
    CUS
    -0.41
    방
    -0.41
    UserScript
    -0.39
    recognized
    -0.39
    POSITIVE LOGITS
     accompanying
    2.59
     accompany
    2.19
     accompanies
    2.15
     associated
    2.05
     concomitant
    1.83
    companying
    1.79
    associated
    1.73
     accompaniment
    1.71
     attached
    1.64
     accompanied
    1.60
    Activations Density 0.919%

    No Known Activations