© 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. 20-GEMMASCOPE-RES-16K
    6. 7059
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear weapons and their consequences

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

    relating to nuclear weapons

    np_acts-logits-general · gemini-2.0-flash

    atomic bomb and nuclear weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gainera
    -0.59
    merkung
    -0.49
    rfloor
    -0.48
     Kraus
    -0.47
     cố
    -0.47
    mascar
    -0.44
     raccomand
    -0.44
     tolua
    -0.44
     Vicki
    -0.44
    Frey
    -0.44
    POSITIVE LOGITS
     nuclear
    1.41
    nuclear
    1.18
     atomic
    1.16
     Nuclear
    1.14
     nukes
    1.13
     nuke
    1.07
    Nuclear
    1.05
     Atomic
    1.03
     Hiroshima
    0.98
     bomb
    0.98
    Activations Density 0.194%

    No Known Activations