© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1302
    Prev
    Next
    INDEX
    Explanations

    references to burning or fire-related actions

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

    references to burning or fire, especially in contexts of damage or destruction.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "burn" and its related contexts of damage, destruction, or harm.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.51
    etcode
    -0.43
    clusal
    -0.42
    aarrggbb
    -0.41
    RTLR
    -0.41
     handleClick
    -0.40
    aktur
    -0.39
    PRNewswire
    -0.39
     TestBed
    -0.38
     useDispatch
    -0.38
    POSITIVE LOGITS
     burn
    2.38
     burned
    2.30
     burnt
    2.19
     burning
    2.19
     Burn
    2.16
     burns
    2.14
    Burn
    2.06
     BURN
    1.98
     Burning
    1.87
    burning
    1.84
    Activations Density 0.238%

    No Known Activations