© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8199
    Prev
    Next
    INDEX
    Explanations

    terms related to kidnapping and hostage situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.32
    AppMethodBeat
    -0.31
     auriculares
    -0.29
     AssemblyCulture
    -0.29
     düz
    -0.29
     ブルゾン
    -0.28
     morire
    -0.28
     fatica
    -0.28
     corriger
    -0.28
     recomendada
    -0.28
    POSITIVE LOGITS
     kidnap
    0.94
     kidna
    0.93
     captivity
    0.92
     kidnapped
    0.85
     captives
    0.83
     Ransom
    0.82
     kidnapping
    0.81
     abduction
    0.78
     hostage
    0.77
     ransom
    0.77
    Activations Density 0.202%

    No Known Activations