© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 102
    Prev
    Next
    INDEX
    Explanations

    security warnings and alerts regarding cyber threats and vulnerabilities

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

    Cyber attacks or vulnerabilities

    np_acts-logits-general · gemini-2.0-flash

    cyber attacks and hacking

    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
     Shreve
    -0.56
    pēc
    -0.54
     BorderRadius
    -0.53
    ouac
    -0.51
    GraphicsUnit
    -0.50
     nocturno
    -0.49
     ModelExpression
    -0.49
     BoxFit
    -0.48
    lorette
    -0.48
     ""],
    -0.48
    POSITIVE LOGITS
     attack
    1.21
     attackers
    1.18
     attacks
    1.12
     attacker
    1.10
     hackers
    1.08
     hacker
    1.05
     malicious
    1.05
     vulnerabilities
    1.02
     hacking
    1.01
     cyber
    1.01
    Activations Density 0.363%

    No Known Activations