© 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. 6749
    Prev
    Next
    INDEX
    Explanations

    references to violent actions or events

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

    killing and violence

    np_acts-logits-general · gemini-2.0-flash

    revenge killings

    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
     незавершена
    -0.70
     للمعارف
    -0.58
     '\\;'
    -0.57
    oa̍t
    -0.56
    tvguidetime
    -0.53
    hoeddwyd
    -0.53
     Signalez
    -0.53
     tartalomajánló
    -0.52
     EconPapers
    -0.51
     ब्रेकडाउन
    -0.51
    POSITIVE LOGITS
     killing
    1.14
     kill
    0.99
     killings
    0.99
     murder
    0.88
     massacres
    0.84
     kills
    0.82
     murderous
    0.82
     murdering
    0.81
     slaughter
    0.81
     murders
    0.80
    Activations Density 0.940%

    No Known Activations