© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 46936
    Prev
    Next
    INDEX
    Explanations

    terms related to kidnapping and abduction

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

    kidnap and kidnapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voldo
    -0.35
    ukone
    -0.34
     exemplu
    -0.32
     ambientes
    -0.32
    而且
    -0.31
     matéria
    -0.31
     relação
    -0.30
     TMPro
    -0.29
    Зноскі
    -0.29
    ัฐ
    -0.29
    POSITIVE LOGITS
     pleaſure
    0.87
     kidnap
    0.79
     kidnapping
    0.78
     ſta
    0.77
     ſche
    0.73
     houſe
    0.72
     ſever
    0.71
     kidnapped
    0.71
     myſelf
    0.69
     abſ
    0.69
    Activations Density 0.008%

    No Known Activations