© 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. 40-GEMMASCOPE-RES-16K
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    incidents of destruction and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.42
    balleur
    -0.37
    makeConstraints
    -0.37
    cobra
    -0.35
    ביוגרפיה
    -0.35
    ızı
    -0.32
    ombres
    -0.32
     ști
    -0.31
     odp
    -0.31
    ensaft
    -0.31
    POSITIVE LOGITS
     destruction
    2.09
     destroyed
    1.95
     destroy
    1.85
     damage
    1.81
     destroying
    1.80
     Destruction
    1.76
     Destroy
    1.73
     destroys
    1.70
    destruction
    1.64
     destru
    1.63
    Activations Density 0.503%

    No Known Activations