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. 15-GEMMASCOPE-RES-16K
    6. 4144
    Prev
    Next
    INDEX
    Explanations

    mentions of surveillance and monitoring practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.83
     '\\;'
    -0.70
    endphp
    -0.64
    MigrationBuilder
    -0.64
    endous
    -0.64
    ]--;
    -0.63
    culously
    -0.63
     forState
    -0.62
     BoxFit
    -0.61
     שוליים
    -0.60
    POSITIVE LOGITS
     surveillance
    0.72
     secretly
    0.65
     undercover
    0.62
     unknowingly
    0.60
     trap
    0.55
     monitoring
    0.53
     surve
    0.52
     Surveillance
    0.52
     traps
    0.51
     Recording
    0.51
    Activations Density 0.386%

    No Known Activations