© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7013
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to death and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cript
    -0.55
    ండి
    -0.53
    cento
    -0.52
    lexia
    -0.52
     كومونز
    -0.51
     Baillargeon
    -0.50
     Ä
    -0.50
    homonymie
    -0.49
    thold
    -0.48
    itana
    -0.48
    POSITIVE LOGITS
     death
    1.53
     deaths
    1.52
     killed
    1.51
     killing
    1.46
     kill
    1.44
     kills
    1.42
    death
    1.33
     DEATH
    1.30
    Death
    1.26
     Death
    1.25
    Activations Density 0.311%

    No Known Activations