© 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. 3627
    Prev
    Next
    INDEX
    Explanations

    references to specific jobs and roles within societal contexts

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

    Third-person singular verbs

    np_acts-logits-general · gemini-2.0-flash

    actions performed by a subject

    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
     ouvriers
    -0.56
     vérit
    -0.54
     travailleurs
    -0.53
    Rüyada
    -0.53
    thalten
    -0.53
     ModelExpression
    -0.52
     voltak
    -0.52
     critères
    -0.50
     domésticos
    -0.50
     äta
    -0.49
    POSITIVE LOGITS
     takes
    1.51
     gets
    1.48
     goes
    1.40
     makes
    1.38
     finds
    1.36
     draws
    1.36
     runs
    1.35
     starts
    1.34
     gives
    1.34
     plays
    1.33
    Activations Density 4.205%

    No Known Activations