© 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. 21-GEMMASCOPE-RES-16K
    11. 13076
    Prev
    Next
    INDEX
    Explanations

    concepts related to justifiable homicide and self-defense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     свя
    -0.45
    CROSSTALK
    -0.45
     exhaustive
    -0.45
    assertArray
    -0.44
    atürk
    -0.43
    livion
    -0.43
    JsonPropertyName
    -0.43
    下载附件
    -0.43
    abbé
    -0.43
    cibo
    -0.42
    POSITIVE LOGITS
     murder
    0.79
     killing
    0.71
     homicide
    0.69
     Murder
    0.65
     homic
    0.65
    murder
    0.65
    Murder
    0.63
     murders
    0.63
     murderer
    0.59
     membunuh
    0.59
    Activations Density 0.536%

    No Known Activations