© 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. 24-GEMMASCOPE-RES-16K
    6. 2673
    Prev
    Next
    INDEX
    Explanations

    instances of job titles and professional roles

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

    Comes before a profession or affiliation

    np_acts-logits-general · gemini-2.0-flash

    joining clauses or items

    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
     themselves
    -0.60
    /
    -0.60
    themselves
    -0.56
    SizeF
    -0.55
     /
    -0.50
    tagHelperRunner
    -0.50
     něj
    -0.49
     sobě
    -0.48
     собой
    -0.48
     quei
    -0.46
    POSITIVE LOGITS
     currently
    1.12
     served
    1.05
    currently
    0.99
     owns
    0.93
     has
    0.93
     worked
    0.92
     member
    0.91
     pernah
    0.91
    served
    0.91
     participated
    0.89
    Activations Density 0.209%

    No Known Activations