© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 6242
    Prev
    Next
    INDEX
    Explanations

    references to suicide or hanging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESTAMP
    -0.45
    Personensuche
    -0.44
    IVEREF
    -0.41
     Gillette
    -0.39
     stamp
    -0.36
    碁
    -0.36
     القدم
    -0.35
     tartalomajánló
    -0.35
    Sqft
    -0.35
    __;
    -0.35
    POSITIVE LOGITS
     hang
    3.44
     hanging
    3.44
     hangs
    3.19
     Hanging
    3.03
     hung
    3.03
     HANG
    3.02
     Hang
    3.00
    Hanging
    2.95
    hanging
    2.89
    Hang
    2.88
    Activations Density 0.712%

    No Known Activations