© 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. 10-GEMMASCOPE-RES-16K
    11. 15436
    Prev
    Next
    INDEX
    Explanations

    statistical references to casualties and civilian injuries in conflict or disaster situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JFrame
    -0.57
     beginnetje
    -0.56
    gegen
    -0.55
    áctica
    -0.55
    tampa
    -0.53
    edoc
    -0.52
    osum
    -0.49
     user
    -0.49
     Google
    -0.49
    стъ
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.65
     casualties
    0.61
     themſelves
    0.61
    NUMX
    0.57
    WaitGroup
    0.57
    ضح
    0.57
     ujednoznacz
    0.56
    ConstraintMaker
    0.56
     reported
    0.56
     fevere
    0.55
    Activations Density 0.160%

    No Known Activations