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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8248
    Prev
    Next
    INDEX
    Explanations

    elements related to socio-political issues, including rights and discrimination

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

    "for" followed by a gerund

    np_acts-logits-general · gemini-2.0-flash

    for complaining, speaking, exercising, taking, daring, marrying

    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
     erfahren
    -0.59
    astify
    -0.58
    stdc
    -0.54
    WithIOException
    -0.51
    pausal
    -0.50
     gero
    -0.50
    الحياه
    -0.49
    aporation
    -0.47
     WQS
    -0.47
    看看
    -0.47
    POSITIVE LOGITS
     having
    1.06
     being
    1.05
    having
    0.95
    being
    0.88
    avoir
    0.83
    Having
    0.80
     haberse
    0.78
    Being
    0.76
     failing
    0.75
     HAVING
    0.73
    Activations Density 0.315%

    No Known Activations