© 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. 0-GEMMASCOPE-RES-16K
    6. 6036
    Prev
    Next
    INDEX
    Explanations

    references to physical pain and injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("../../
    -0.64
     "../../
    -0.52
     '../../
    -0.51
    ('../../
    -0.51
    I
    -0.51
    <eos>
    -0.50
     hered
    -0.50
    enumi
    -0.49
    gin
    -0.49
     yaptı
    -0.49
    POSITIVE LOGITS
     sorrow
    1.40
     grief
    1.31
     worry
    1.26
     hurt
    1.11
     sadness
    1.10
     pain
    1.09
     anger
    1.08
     Sorrow
    1.08
     shame
    1.07
     harm
    1.04
    Activations Density 0.101%

    No Known Activations