© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8621
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scolaires
    -0.86
     שוליים
    -0.83
     vectorielles
    -0.82
     pouvoit
    -0.80
     suivie
    -0.80
    endphp
    -0.80
     auroit
    -0.77
     dépos
    -0.77
     mourut
    -0.76
     fermés
    -0.76
    POSITIVE LOGITS
     security
    0.96
     Security
    0.91
     lock
    0.87
    Security
    0.86
    cr
    0.77
     Es
    0.76
     Lock
    0.75
     es
    0.75
     SECURITY
    0.67
    cf
    0.66
    Activations Density 0.262%

    No Known Activations