© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9338
    Prev
    Next
    INDEX
    Explanations

    references to suicide and self-harm in various contexts

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

    "suicide" or "suicidal"

    np_acts-logits-general · gemini-2.0-flash

    suicide and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.38
    webElementXpaths
    -0.38
    +#+
    -0.37
    новниш
    -0.36
     supers
    -0.34
     للمعارف
    -0.32
     Workers
    -0.32
     WORKERS
    -0.32
     незавершена
    -0.31
     Lazy
    -0.31
    POSITIVE LOGITS
     suicide
    2.00
    suicide
    1.67
    Suicide
    1.66
     suicidal
    1.65
     Suicide
    1.65
     suicides
    1.55
     suic
    1.42
     suicidio
    1.38
    自殺
    1.38
    自杀
    1.23
    Activations Density 0.257%

    No Known Activations