© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4241
    Prev
    Next
    INDEX
    Explanations

    references to blood or bleeding

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

    relating to blood or fluid coming out

    np_acts-logits-general · gemini-2.0-flash

    leaking and bleeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.60
    numerusform
    -0.53
    sna
    -0.50
    arynx
    -0.49
     Jann
    -0.48
     ['$
    -0.47
    eryllium
    -0.46
    cmds
    -0.46
     ***!
    -0.46
     Zusch
    -0.46
    POSITIVE LOGITS
     leaking
    1.43
     leak
    1.42
     leaks
    1.40
     leakage
    1.29
     leaked
    1.27
    leak
    1.21
     Leaks
    1.18
     Leak
    1.10
     bleeding
    1.07
     bleed
    1.04
    Activations Density 0.247%

    No Known Activations