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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5862
    Prev
    Next
    INDEX
    Explanations

    keywords related to fire incidents and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    death or destruction

    np_acts-logits-general · gemini-2.0-flash

    killed, claimed, burned, took

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldBuilder
    -0.59
    ngOn
    -0.58
     Avoiding
    -0.57
     scher
    -0.57
    CPtr
    -0.54
     Gets
    -0.54
     initComponents
    -0.53
    GenerationType
    -0.53
     {}),
    -0.53
    Avoiding
    -0.53
    POSITIVE LOGITS
     killed
    0.92
     claimed
    0.90
     claim
    0.82
     claiming
    0.82
    claim
    0.78
     kill
    0.75
    claimed
    0.75
     decim
    0.72
     CLAIM
    0.72
     claims
    0.70
    Activations Density 0.228%

    No Known Activations