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. 23-GEMMASCOPE-RES-16K
    6. 8937
    Prev
    Next
    INDEX
    Explanations

    references to inflicting pain and suffering, particularly concerning ethical dilemmas related to animals and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.54
     connexes
    -0.53
    <bos>
    -0.51
     Effectiveness
    -0.50
    tagHelper
    -0.49
     referenties
    -0.46
    ')['
    -0.44
    ganet
    -0.44
     Verhältnis
    -0.44
    seende
    -0.43
    POSITIVE LOGITS
     misery
    1.08
     injury
    1.03
     pain
    1.03
     harm
    1.02
     illness
    1.02
     distress
    0.99
     sickness
    0.97
     unhappiness
    0.97
     hardship
    0.96
     disorder
    0.95
    Activations Density 1.014%

    No Known Activations