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. 18-GEMMASCOPE-RES-16K
    6. 3826
    Prev
    Next
    INDEX
    Explanations

    terms related to terrorism and militant activities

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

    Terrorist attacks and groups

    np_acts-logits-general · gemini-2.0-flash

    terrorism and bombings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sutter
    -0.47
    |}{$
    -0.47
    }{||
    -0.46
     Kli
    -0.46
     protokol
    -0.42
    луй
    -0.41
    <bos>
    -0.41
     partage
    -0.41
     Sailing
    -0.41
    DebuggerNonUser
    -0.41
    POSITIVE LOGITS
     terrorist
    1.37
     bomb
    1.35
     terrorism
    1.29
    bomb
    1.23
     terrorists
    1.20
     bombing
    1.18
     explosives
    1.16
     bombings
    1.15
     bombs
    1.14
    Bomb
    1.13
    Activations Density 0.200%

    No Known Activations