Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3612
    Prev
    Next
    INDEX
    Explanations

    terms related to ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ravel
    -0.59
    jev
    -0.53
     middel
    -0.52
    inheritDoc
    -0.51
    Pel
    -0.50
    os
    -0.50
    đ
    -0.48
    arum
    -0.48
    エン
    -0.47
    un
    -0.47
    POSITIVE LOGITS
     ethics
    1.15
    ethical
    1.13
    ThroughAttribute
    1.11
     editions
    1.10
     Ethical
    1.08
     Edition
    1.06
     ethical
    1.05
     Ethics
    1.04
     Editions
    1.02
    edition
    1.01
    Activations Density 0.067%

    No Known Activations