© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8189
    Prev
    Next
    INDEX
    Explanations

    references to security or guarding, particularly in a protective or military context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.47
     للاسماء
    -0.46
    
    -0.45
    Enqueue
    -0.45
     etme
    -0.43
     leveraged
    -0.42
    libft
    -0.42
    ilever
    -0.42
    Tracce
    -0.41
    internalType
    -0.40
    POSITIVE LOGITS
     guard
    1.66
     Guard
    1.46
    Guard
    1.41
    guard
    1.34
     guards
    1.20
     GUARD
    1.15
    GUARD
    1.05
     guarding
    1.02
    guards
    1.00
     Guards
    0.99
    Activations Density 0.161%

    No Known Activations